From 148bd343f3e7e32d141f66b5b5c9b98b2975b0b3 Mon Sep 17 00:00:00 2001 From: "Roberto C. Sanchez" Date: Sat, 29 Mar 2014 10:53:52 -0400 Subject: Imported Upstream version 1.5.8 --- src/modules/filters/Makefile | 5 - src/modules/filters/Makefile.am | 92 --- src/modules/filters/cipherfil.cpp | 44 -- src/modules/filters/gbffootnotes.cpp | 197 ------- src/modules/filters/gbfheadings.cpp | 92 --- src/modules/filters/gbfhtml.cpp | 168 ------ src/modules/filters/gbfhtmlhref.cpp | 229 -------- src/modules/filters/gbfmorph.cpp | 82 --- src/modules/filters/gbfosis.cpp | 439 -------------- src/modules/filters/gbfplain.cpp | 95 --- src/modules/filters/gbfredletterwords.cpp | 98 ---- src/modules/filters/gbfrtf.cpp | 289 ---------- src/modules/filters/gbfstrongs.cpp | 116 ---- src/modules/filters/gbfthml.cpp | 216 ------- src/modules/filters/gbfwebif.cpp | 161 ------ src/modules/filters/greeklexattribs.cpp | 100 ---- src/modules/filters/latin1utf16.cpp | 119 ---- src/modules/filters/latin1utf8.cpp | 173 ------ src/modules/filters/osisfootnotes.cpp | 138 ----- src/modules/filters/osisheadings.cpp | 118 ---- src/modules/filters/osishtmlhref.cpp | 339 ----------- src/modules/filters/osislemma.cpp | 78 --- src/modules/filters/osismorph.cpp | 75 --- src/modules/filters/osisplain.cpp | 151 ----- src/modules/filters/osisredletterwords.cpp | 77 --- src/modules/filters/osisrtf.cpp | 333 ----------- src/modules/filters/osisscripref.cpp | 104 ---- src/modules/filters/osisstrongs.cpp | 128 ----- src/modules/filters/osiswebif.cpp | 212 ------- src/modules/filters/plainfootnotes.cpp | 83 --- src/modules/filters/plainhtml.cpp | 70 --- src/modules/filters/rtfhtml.cpp | 80 --- src/modules/filters/scsuutf8.cpp | 226 -------- src/modules/filters/swbasicfilter.cpp | 321 ----------- src/modules/filters/swoptfilter.cpp | 38 -- src/modules/filters/thmlfootnotes.cpp | 127 ----- src/modules/filters/thmlgbf.cpp | 283 --------- src/modules/filters/thmlheadings.cpp | 96 ---- src/modules/filters/thmlhtml.cpp | 226 -------- src/modules/filters/thmlhtmlhref.cpp | 209 ------- src/modules/filters/thmllemma.cpp | 69 --- src/modules/filters/thmlmorph.cpp | 69 --- src/modules/filters/thmlosis.cpp | 385 ------------- src/modules/filters/thmlplain.cpp | 210 ------- src/modules/filters/thmlrtf.cpp | 314 ---------- src/modules/filters/thmlscripref.cpp | 126 ---- src/modules/filters/thmlstrongs.cpp | 139 ----- src/modules/filters/thmlvariants.cpp | 112 ---- src/modules/filters/thmlwebif.cpp | 104 ---- src/modules/filters/unicodertf.cpp | 86 --- src/modules/filters/utf16utf8.cpp | 92 --- src/modules/filters/utf8arshaping.cpp | 52 -- src/modules/filters/utf8bidireorder.cpp | 61 -- src/modules/filters/utf8cantillation.cpp | 55 -- src/modules/filters/utf8greekaccents.cpp | 249 -------- src/modules/filters/utf8hebrewpoints.cpp | 44 -- src/modules/filters/utf8html.cpp | 69 --- src/modules/filters/utf8latin1.cpp | 74 --- src/modules/filters/utf8nfc.cpp | 53 -- src/modules/filters/utf8nfkd.cpp | 53 -- src/modules/filters/utf8transliterator.cpp | 889 ----------------------------- src/modules/filters/utf8utf16.cpp | 78 --- 62 files changed, 9610 deletions(-) delete mode 100644 src/modules/filters/Makefile delete mode 100644 src/modules/filters/Makefile.am delete mode 100644 src/modules/filters/cipherfil.cpp delete mode 100644 src/modules/filters/gbffootnotes.cpp delete mode 100644 src/modules/filters/gbfheadings.cpp delete mode 100644 src/modules/filters/gbfhtml.cpp delete mode 100644 src/modules/filters/gbfhtmlhref.cpp delete mode 100644 src/modules/filters/gbfmorph.cpp delete mode 100644 src/modules/filters/gbfosis.cpp delete mode 100644 src/modules/filters/gbfplain.cpp delete mode 100644 src/modules/filters/gbfredletterwords.cpp delete mode 100644 src/modules/filters/gbfrtf.cpp delete mode 100644 src/modules/filters/gbfstrongs.cpp delete mode 100644 src/modules/filters/gbfthml.cpp delete mode 100644 src/modules/filters/gbfwebif.cpp delete mode 100644 src/modules/filters/greeklexattribs.cpp delete mode 100644 src/modules/filters/latin1utf16.cpp delete mode 100644 src/modules/filters/latin1utf8.cpp delete mode 100644 src/modules/filters/osisfootnotes.cpp delete mode 100644 src/modules/filters/osisheadings.cpp delete mode 100644 src/modules/filters/osishtmlhref.cpp delete mode 100644 src/modules/filters/osislemma.cpp delete mode 100644 src/modules/filters/osismorph.cpp delete mode 100644 src/modules/filters/osisplain.cpp delete mode 100644 src/modules/filters/osisredletterwords.cpp delete mode 100644 src/modules/filters/osisrtf.cpp delete mode 100644 src/modules/filters/osisscripref.cpp delete mode 100644 src/modules/filters/osisstrongs.cpp delete mode 100644 src/modules/filters/osiswebif.cpp delete mode 100644 src/modules/filters/plainfootnotes.cpp delete mode 100644 src/modules/filters/plainhtml.cpp delete mode 100644 src/modules/filters/rtfhtml.cpp delete mode 100644 src/modules/filters/scsuutf8.cpp delete mode 100644 src/modules/filters/swbasicfilter.cpp delete mode 100644 src/modules/filters/swoptfilter.cpp delete mode 100644 src/modules/filters/thmlfootnotes.cpp delete mode 100644 src/modules/filters/thmlgbf.cpp delete mode 100644 src/modules/filters/thmlheadings.cpp delete mode 100644 src/modules/filters/thmlhtml.cpp delete mode 100644 src/modules/filters/thmlhtmlhref.cpp delete mode 100644 src/modules/filters/thmllemma.cpp delete mode 100644 src/modules/filters/thmlmorph.cpp delete mode 100644 src/modules/filters/thmlosis.cpp delete mode 100644 src/modules/filters/thmlplain.cpp delete mode 100644 src/modules/filters/thmlrtf.cpp delete mode 100644 src/modules/filters/thmlscripref.cpp delete mode 100644 src/modules/filters/thmlstrongs.cpp delete mode 100644 src/modules/filters/thmlvariants.cpp delete mode 100644 src/modules/filters/thmlwebif.cpp delete mode 100644 src/modules/filters/unicodertf.cpp delete mode 100644 src/modules/filters/utf16utf8.cpp delete mode 100644 src/modules/filters/utf8arshaping.cpp delete mode 100644 src/modules/filters/utf8bidireorder.cpp delete mode 100644 src/modules/filters/utf8cantillation.cpp delete mode 100644 src/modules/filters/utf8greekaccents.cpp delete mode 100644 src/modules/filters/utf8hebrewpoints.cpp delete mode 100644 src/modules/filters/utf8html.cpp delete mode 100644 src/modules/filters/utf8latin1.cpp delete mode 100644 src/modules/filters/utf8nfc.cpp delete mode 100644 src/modules/filters/utf8nfkd.cpp delete mode 100644 src/modules/filters/utf8transliterator.cpp delete mode 100644 src/modules/filters/utf8utf16.cpp (limited to 'src/modules/filters') diff --git a/src/modules/filters/Makefile b/src/modules/filters/Makefile deleted file mode 100644 index 1a2d00d..0000000 --- a/src/modules/filters/Makefile +++ /dev/null @@ -1,5 +0,0 @@ - -root := ../../.. - -all: - make -C ${root} diff --git a/src/modules/filters/Makefile.am b/src/modules/filters/Makefile.am deleted file mode 100644 index c9a6bef..0000000 --- a/src/modules/filters/Makefile.am +++ /dev/null @@ -1,92 +0,0 @@ -filtersdir = $(top_srcdir)/src/modules/filters - -libsword_la_SOURCES += $(filtersdir)/swbasicfilter.cpp -libsword_la_SOURCES += $(filtersdir)/swoptfilter.cpp - -libsword_la_SOURCES += $(filtersdir)/gbfhtml.cpp -libsword_la_SOURCES += $(filtersdir)/gbfhtmlhref.cpp -libsword_la_SOURCES += $(filtersdir)/gbfwebif.cpp -libsword_la_SOURCES += $(filtersdir)/gbfplain.cpp -libsword_la_SOURCES += $(filtersdir)/gbfrtf.cpp -libsword_la_SOURCES += $(filtersdir)/plainhtml.cpp -libsword_la_SOURCES += $(filtersdir)/cipherfil.cpp -libsword_la_SOURCES += $(filtersdir)/rtfhtml.cpp - -libsword_la_SOURCES += $(filtersdir)/gbfstrongs.cpp -libsword_la_SOURCES += $(filtersdir)/gbffootnotes.cpp -libsword_la_SOURCES += $(filtersdir)/gbfheadings.cpp -libsword_la_SOURCES += $(filtersdir)/gbfredletterwords.cpp -libsword_la_SOURCES += $(filtersdir)/gbfmorph.cpp -libsword_la_SOURCES += $(filtersdir)/plainfootnotes.cpp - -libsword_la_SOURCES += $(filtersdir)/thmlstrongs.cpp -libsword_la_SOURCES += $(filtersdir)/thmlfootnotes.cpp -libsword_la_SOURCES += $(filtersdir)/thmlheadings.cpp -libsword_la_SOURCES += $(filtersdir)/thmlmorph.cpp -libsword_la_SOURCES += $(filtersdir)/thmllemma.cpp -libsword_la_SOURCES += $(filtersdir)/thmlscripref.cpp -libsword_la_SOURCES += $(filtersdir)/thmlvariants.cpp - -libsword_la_SOURCES += $(filtersdir)/gbfthml.cpp -libsword_la_SOURCES += $(filtersdir)/thmlgbf.cpp -libsword_la_SOURCES += $(filtersdir)/thmlrtf.cpp -libsword_la_SOURCES += $(filtersdir)/thmlhtml.cpp -libsword_la_SOURCES += $(filtersdir)/thmlhtmlhref.cpp -libsword_la_SOURCES += $(filtersdir)/thmlwebif.cpp - -libsword_la_SOURCES += $(filtersdir)/thmlosis.cpp -libsword_la_SOURCES += $(filtersdir)/gbfosis.cpp -libsword_la_SOURCES += $(filtersdir)/thmlplain.cpp - -libsword_la_SOURCES += $(filtersdir)/osisheadings.cpp -libsword_la_SOURCES += $(filtersdir)/osisfootnotes.cpp -libsword_la_SOURCES += $(filtersdir)/osishtmlhref.cpp -libsword_la_SOURCES += $(filtersdir)/osiswebif.cpp -libsword_la_SOURCES += $(filtersdir)/osismorph.cpp -libsword_la_SOURCES += $(filtersdir)/osisstrongs.cpp -libsword_la_SOURCES += $(filtersdir)/osisplain.cpp -libsword_la_SOURCES += $(filtersdir)/osisrtf.cpp -libsword_la_SOURCES += $(filtersdir)/osislemma.cpp -libsword_la_SOURCES += $(filtersdir)/osisredletterwords.cpp -libsword_la_SOURCES += $(filtersdir)/osisscripref.cpp - -libsword_la_SOURCES += $(filtersdir)/unicodertf.cpp -libsword_la_SOURCES += $(filtersdir)/latin1utf8.cpp -libsword_la_SOURCES += $(filtersdir)/latin1utf16.cpp -libsword_la_SOURCES += $(filtersdir)/utf8utf16.cpp -libsword_la_SOURCES += $(filtersdir)/utf16utf8.cpp -libsword_la_SOURCES += $(filtersdir)/scsuutf8.cpp -libsword_la_SOURCES += $(filtersdir)/utf8html.cpp -libsword_la_SOURCES += $(filtersdir)/utf8latin1.cpp - -libsword_la_SOURCES += $(filtersdir)/utf8cantillation.cpp -libsword_la_SOURCES += $(filtersdir)/utf8hebrewpoints.cpp -libsword_la_SOURCES += $(filtersdir)/utf8greekaccents.cpp - -libsword_la_SOURCES += $(filtersdir)/greeklexattribs.cpp - -SWICUSRC = $(filtersdir)/utf8transliterator.cpp -SWICUSRC += $(filtersdir)/utf8nfc.cpp -SWICUSRC += $(filtersdir)/utf8nfkd.cpp -SWICUSRC += $(filtersdir)/utf8arshaping.cpp -SWICUSRC += $(filtersdir)/utf8bidireorder.cpp - -if ICU -ICUDEFS = -D_ICU_ -DISTSWICUSRC = -SWREALICUSRC = $(SWICUSRC) -else -if ICUSWORD -ICUDEFS = -D_ICU_ -D_ICUSWORD_ -DISTSWICUSRC = -SWREALICUSRC = $(SWICUSRC) -else -DISTSWICUSRC = $(SWICUSRC) -SWREALICUSRC = -endif -endif - -INCLUDES += $(ICUDEFS) -libsword_la_SOURCES += $(SWREALICUSRC) -EXTRA_DIST = $(DISTSWICUSRC) - diff --git a/src/modules/filters/cipherfil.cpp b/src/modules/filters/cipherfil.cpp deleted file mode 100644 index abdd0fc..0000000 --- a/src/modules/filters/cipherfil.cpp +++ /dev/null @@ -1,44 +0,0 @@ -/****************************************************************************** - * - * cipherfil - SWFilter descendant to decipher a module - */ - - -#include -#include - -SWORD_NAMESPACE_START - -CipherFilter::CipherFilter(const char *key) { - cipher = new SWCipher((unsigned char *)key); -} - - -CipherFilter::~CipherFilter() { - delete cipher; -} - - -SWCipher *CipherFilter::getCipher() { - return cipher; -} - - -char CipherFilter::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - if (text.length() > 2) { //check if it's large enough to substract 2 in the next step. - unsigned long len = text.length(); - if (!key) { // hack, using key to determine encipher, or decipher - cipher->cipherBuf(&len, text.getRawData()); //set buffer to enciphered text - memcpy(text.getRawData(), cipher->Buf(), len); -// text = cipher->Buf(); //get the deciphered buffer - } - else if ((unsigned long)key == 1) { - cipher->Buf(text.getRawData(), len); - memcpy(text.getRawData(), cipher->cipherBuf(&len), len); -// text = cipher->cipherBuf(&len); - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/gbffootnotes.cpp b/src/modules/filters/gbffootnotes.cpp deleted file mode 100644 index 38f1106..0000000 --- a/src/modules/filters/gbffootnotes.cpp +++ /dev/null @@ -1,197 +0,0 @@ -/****************************************************************************** - * - * gbffootnotes - SWFilter descendant to hide or show footnotes - * in a GBF module. - */ - - -#include -#include -#include -#include -#include -#include -#ifndef __GNUC__ -#else -#include -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Footnotes"; -const char oTip[] = "Toggles Footnotes On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - - -GBFFootnotes::GBFFootnotes() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -GBFFootnotes::~GBFFootnotes() { -} - - -char GBFFootnotes::processText (SWBuf &text, const SWKey *key, const SWModule *module) -{ - - SWBuf token; - bool intoken = false; - bool hide = false; - SWBuf tagText; - XMLTag startTag; - SWBuf refs = ""; - int footnoteNum = 1; - char buf[254]; - VerseKey parser = key->getText(); - - SWBuf orig = text; - const char *from = orig.c_str(); - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - token = ""; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - - XMLTag tag(token); - if (!strcmp(tag.getName(), "RF")) { - refs = ""; - startTag = tag; - hide = true; - tagText = ""; - continue; - } - else if (!strcmp(tag.getName(), "Rf")) { - if (module->isProcessEntryAttributes()) { - if(tagText.length() == 1 || !strcmp(module->Name(), "IGNT")) { - if (option) { // for ASV marks text in verse then put explanation at end of verse - text += " ("; - text.append(tagText); - text += ")"; - hide = false; - continue; - } - } - SWBuf fc = module->getEntryAttributes()["Footnote"]["count"]["value"]; - footnoteNum = (fc.length()) ? atoi(fc.c_str()) : 0; - sprintf(buf, "%i", ++footnoteNum); - module->getEntryAttributes()["Footnote"]["count"]["value"] = buf; - StringList attributes = startTag.getAttributeNames(); - for (StringList::iterator it = attributes.begin(); it != attributes.end(); it++) { - module->getEntryAttributes()["Footnote"][buf][it->c_str()] = startTag.getAttribute(it->c_str()); - } - module->getEntryAttributes()["Footnote"][buf]["body"] = tagText; - startTag.setAttribute("swordFootnote", buf); - } - hide = false; - if (option) { - text += startTag; - text.append(tagText); - } - else continue; - } - if (!hide) { - text += '<'; - text.append(token); - text += '>'; - } - else { - tagText += '<'; - tagText.append(token); - tagText += '>'; - } - continue; - } - if (intoken) { //copy token - token += *from; - } - else if (!hide) { //copy text which is not inside a token - text += *from; - } - else tagText += *from; - } - return 0; - - - - - - - - - /* - if (!option) { // if we don't want footnotes - char token[4096]; // cheese. Fix. - int tokpos = 0; - bool intoken = false; - int len; - bool hide = false; - - const char *from; - SWBuf orig = text; - from = orig.c_str(); - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - tokpos = 0; -// memset(token, 0, 4096); - token[0] = 0; - token[1] = 0; - token[2] = 0; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - switch (*token) { - case 'R': // Reference - switch(token[1]) { - case 'F': // Begin footnote - hide = true; - break; - case 'f': // end footnote - hide = false; - break; - } - continue; // skip token - case 'W': - if (token[1] == 'T') { - switch (token[2]) { - case 'P': - case 'S': - case 'A': - continue; // remove this token - default: - break; - } - } - } - // if not a footnote token, keep token in text - if (!hide) { - text += '<'; - text += token; - text += '>'; - } - continue; - } - if (intoken) { - if (tokpos < 4090) - token[tokpos++] = *from; - token[tokpos+2] = 0; // +2 cuz we init token with 2 extra '0' because of switch statement - } - else { - if (!hide) { - text += *from; - } - } - } - } - return 0;*/ -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/gbfheadings.cpp b/src/modules/filters/gbfheadings.cpp deleted file mode 100644 index 01a34ca..0000000 --- a/src/modules/filters/gbfheadings.cpp +++ /dev/null @@ -1,92 +0,0 @@ -/****************************************************************************** - * - * gbfheadings - SWFilter descendant to hide or show headings - * in a GBF module. - */ - - -#include -#include -#ifndef __GNUC__ -#else -#include -#endif - -SWORD_NAMESPACE_START - - -const char oName[] = "Headings"; -const char oTip[] = "Toggles Headings On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -GBFHeadings::GBFHeadings() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -GBFHeadings::~GBFHeadings() { -} - - -char GBFHeadings::processText (SWBuf &text, const SWKey *key, const SWModule *module) { - if (!option) { // if we don't want headings - char token[2048]; // cheese. Fix. - int tokpos = 0; - bool intoken = false; - int len; - bool hide = false; - - const char *from; - SWBuf orig = text; - from = orig.c_str(); - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - tokpos = 0; -// memset(token, 0, 2048); - token[0] = 0; - token[1] = 0; - token[2] = 0; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - switch (*token) { - case 'T': // Reference - switch(token[1]) { - case 'S': // Begin heading - hide = true; - break; - case 's': // end heading - hide = false; - break; - } - continue; // skip token - } - // if not a heading token, keep token in text - if (!hide) { - text += '<'; - for (char *tok = token; *tok; tok++) - text += *tok; - text += '>'; - } - continue; - } - if (intoken) { - if (tokpos < 2045) - token[tokpos++] = *from; - token[tokpos+2] = 0; - } - else { - if (!hide) { - text += *from; - } - } - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/gbfhtml.cpp b/src/modules/filters/gbfhtml.cpp deleted file mode 100644 index 775bc06..0000000 --- a/src/modules/filters/gbfhtml.cpp +++ /dev/null @@ -1,168 +0,0 @@ -/*************************************************************************** - gbfhtml.cpp - GBF to HTML filter - ------------------- - begin : 2001-09-03 - copyright : 2001 by CrossWire Bible Society - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include -#include -#include - -SWORD_NAMESPACE_START - -GBFHTML::GBFHTML() { - setTokenStart("<"); - setTokenEnd(">"); - - setTokenCaseSensitive(true); - - addTokenSubstitute("Rf", ")"); - addTokenSubstitute("Rx", ""); - addTokenSubstitute("FI", ""); // italics begin - addTokenSubstitute("Fi", ""); - addTokenSubstitute("FB", ""); // bold begin - addTokenSubstitute("Fb", ""); - addTokenSubstitute("FR", ""); // words of Jesus begin - addTokenSubstitute("Fr", ""); - addTokenSubstitute("FU", ""); // underline begin - addTokenSubstitute("Fu", ""); - addTokenSubstitute("FO", ""); // Old Testament quote begin - addTokenSubstitute("Fo", ""); - addTokenSubstitute("FS", ""); // Superscript begin// Subscript begin - addTokenSubstitute("Fs", ""); - addTokenSubstitute("FV", ""); // Subscript begin - addTokenSubstitute("Fv", ""); - addTokenSubstitute("TT", ""); // Book title begin - addTokenSubstitute("Tt", ""); - addTokenSubstitute("PP", ""); // poetry begin - addTokenSubstitute("Pp", ""); - addTokenSubstitute("Fn", ""); // font end - addTokenSubstitute("CL", "
"); // new line - addTokenSubstitute("CM", "
"); // paragraph is a non showing comment that can be changed in the front end to

if desired - addTokenSubstitute("CG", ""); // ??? - addTokenSubstitute("CT", ""); // ??? - addTokenSubstitute("JR", "

"); // right align begin - addTokenSubstitute("JC", "
"); // center align begin - addTokenSubstitute("JL", "
"); // align end - -} - - -bool GBFHTML::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) { - const char *tok; - char val[128]; - char *valto; - const char *num; - MyUserData *u = (MyUserData *)userData; - - if (!substituteToken(buf, token)) { - // deal with OSIS note tags. Just hide till OSISRTF - if (!strncmp(token, "note ", 5)) { - // let's stop text from going to output - u->suspendTextPassThru = true; - } - - else if (!strncmp(token, "/note", 5)) { - u->suspendTextPassThru = false; - } - - else if (!strncmp(token, "w", 1)) { - // OSIS Word (temporary until OSISRTF is done) - valto = val; - num = strstr(token, "lemma=\"x-Strongs:"); - if (num) { - for (num+=17; ((*num) && (*num != '\"')); num++) - *valto++ = *num; - *valto = 0; - if (atoi((!isdigit(*val))?val+1:val) < 5627) { - buf += " <"; - for (tok = (!isdigit(*val))?val+1:val; *tok; tok++) - buf += *tok; - buf += "> "; - } - } - valto = val; - num = strstr(token, "morph=\"x-Robinson:"); - if (num) { - for (num+=18; ((*num) && (*num != '\"')); num++) - *valto++ = *num; - *valto = 0; - // normal robinsons tense - buf += " ("; - for (tok = val; *tok; tok++) - buf += *tok; - buf += ") "; - } - } - - else if (!strncmp(token, "WG", 2) || !strncmp(token, "WH", 2)) { // strong's numbers - buf += " <"; - for (tok = token + 2; *tok; tok++) - buf += *tok; - buf += "> "; - } - - else if (!strncmp(token, "WTG", 3) || !strncmp(token, "WTH", 3)) { // strong's numbers tense - buf += " <"; - for (tok = token + 3; *tok; tok++) - if(*tok != '\"') - buf += *tok; - buf += ") "; - } - - else if (!strncmp(token, "RX", 2)) { - buf += ""; - for (tok = token + 3; *tok; tok++) { - if(*tok != '<' && *tok+1 != 'R' && *tok+2 != 'x') { - buf += *tok; - } - else { - break; - } - } - buf += ""; - } - - else if (!strncmp(token, "RB", 2)) { - buf += ""; - u->hasFootnotePreTag = true; - } - - else if (!strncmp(token, "RF", 2)) { - if (u->hasFootnotePreTag) { - u->hasFootnotePreTag = false; - buf += " "; - } - buf += " ("; - } - - else if (!strncmp(token, "FN", 2)) { - buf += ""; - } - - else if (!strncmp(token, "CA", 2)) { // ASCII value - buf += (char)atoi(&token[2]); - } - - else { - return false; - } - } - return true; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/gbfhtmlhref.cpp b/src/modules/filters/gbfhtmlhref.cpp deleted file mode 100644 index 4061150..0000000 --- a/src/modules/filters/gbfhtmlhref.cpp +++ /dev/null @@ -1,229 +0,0 @@ -/*************************************************************************** - gbfhtmlhref.cpp - GBF to HTML filter with hrefs - for strongs and morph tags - ------------------- - begin : 2001-09-03 - copyright : 2001 by CrossWire Bible Society - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include -#include -#include -#include -#include -#include - -SWORD_NAMESPACE_START - -GBFHTMLHREF::GBFHTMLHREF() { - setTokenStart("<"); - setTokenEnd(">"); - - setTokenCaseSensitive(true); - - //addTokenSubstitute("Rf", ")"); - addTokenSubstitute("FA", ""); // for ASV footnotes to mark text - addTokenSubstitute("Rx", ""); - addTokenSubstitute("FI", ""); // italics begin - addTokenSubstitute("Fi", ""); - addTokenSubstitute("FB", ""); // bold begin - addTokenSubstitute("Fb", ""); - addTokenSubstitute("FR", ""); // words of Jesus begin - addTokenSubstitute("Fr", ""); - addTokenSubstitute("FU", ""); // underline begin - addTokenSubstitute("Fu", ""); - addTokenSubstitute("FO", ""); // Old Testament quote begin - addTokenSubstitute("Fo", ""); - addTokenSubstitute("FS", ""); // Superscript begin// Subscript begin - addTokenSubstitute("Fs", ""); - addTokenSubstitute("FV", ""); // Subscript begin - addTokenSubstitute("Fv", ""); - addTokenSubstitute("TT", ""); // Book title begin - addTokenSubstitute("Tt", ""); - addTokenSubstitute("PP", ""); // poetry begin - addTokenSubstitute("Pp", ""); - addTokenSubstitute("Fn", ""); // font end - addTokenSubstitute("CL", "
"); // new line - addTokenSubstitute("CM", "
"); // paragraph is a non showing comment that can be changed in the front end to

if desired - addTokenSubstitute("CG", ""); // ??? - addTokenSubstitute("CT", ""); // ??? - addTokenSubstitute("JR", "

"); // right align begin - addTokenSubstitute("JC", "
"); // center align begin - addTokenSubstitute("JL", "
"); // align end - -} - - -bool GBFHTMLHREF::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) { - const char *tok; - char val[128]; - char *valto; - const char *num; - MyUserData *u = (MyUserData *)userData; - - if (!substituteToken(buf, token)) { - XMLTag tag(token); - if (!strncmp(token, "w", 1)) { - // OSIS Word (temporary until OSISRTF is done) - valto = val; - num = strstr(token, "lemma=\"x-Strongs:"); - if (num) { - for (num+=17; ((*num) && (*num != '\"')); num++) - *valto++ = *num; - *valto = 0; - if (atoi((!isdigit(*val))?val+1:val) < 5627) { - buf += " <"; - for (tok = (!isdigit(*val))?val+1:val; *tok; tok++) - buf += *tok; - buf += "> "; - //cout << buf; - - } - /* forget these for now - else { - // verb morph - sprintf(wordstr, "%03d", word-1); - module->getEntryAttributes()["Word"][wordstr]["Morph"] = val; - } - */ - } - valto = val; - num = strstr(token, "morph=\"x-Robinson:"); - if (num) { - for (num+=18; ((*num) && (*num != '\"')); num++) - *valto++ = *num; - *valto = 0; - buf += " ("; - for (tok = val; *tok; tok++) - //if(*tok != '\"') - buf += *tok; - buf += ") "; - } - } - - else if (!strncmp(token, "WG", 2) || !strncmp(token, "WH", 2)) { // strong's numbers - buf += " <"; - for (tok = token + 2; *tok; tok++) - //if(token[i] != '\"') - buf += *tok; - buf += ">"; - } - - else if (!strncmp(token, "WTG", 3) || !strncmp(token, "WTH", 3)) { // strong's numbers tense - buf += " ("; - for (tok = token + 3; *tok; tok++) - if(*tok != '\"') - buf += *tok; - buf += ")"; - } - - else if (!strncmp(token, "WT", 2) && strncmp(token, "WTH", 3) && strncmp(token, "WTG", 3)) { // morph tags - buf += " ("; - for (tok = token + 2; *tok; tok++) - if(*tok != '\"') - buf += *tok; - buf += ")"; - } - - else if (!strcmp(tag.getName(), "RX")) { - buf += ""; - } - else if (!strcmp(tag.getName(), "RF")) { - SWBuf type = tag.getAttribute("type"); - SWBuf footnoteNumber = tag.getAttribute("swordFootnote"); - VerseKey *vkey; - // see if we have a VerseKey * or descendant - try { - vkey = SWDYNAMIC_CAST(VerseKey, u->key); - } - catch ( ... ) { } - if (vkey) { - // leave this special osis type in for crossReference notes types? Might thml use this some day? Doesn't hurt. - //char ch = ((tag.getAttribute("type") && ((!strcmp(tag.getAttribute("type"), "crossReference")) || (!strcmp(tag.getAttribute("type"), "x-cross-ref")))) ? 'x':'n'); - buf.appendFormatted("*%c ", vkey->getText(), 'n', footnoteNumber.c_str(), 'n'); - } - u->suspendTextPassThru = true; - } - else if (!strcmp(tag.getName(), "Rf")) { - u->suspendTextPassThru = false; - } -/* - else if (!strncmp(token, "RB", 2)) { - buf += " "; - u->hasFootnotePreTag = true; - } - - else if (!strncmp(token, "Rf", 2)) { - buf += " lastTextNode.c_str(); - buf += "\">"; - buf += "*n "; - // let's let text resume to output again - u->suspendTextPassThru = false; - } - - else if (!strncmp(token, "RF", 2)) { - if (u->hasFootnotePreTag) { - u->hasFootnotePreTag = false; - buf += " "; - } - u->suspendTextPassThru = true; - } -*/ - else if (!strncmp(token, "FN", 2)) { - buf += ""; - } - - else if (!strncmp(token, "CA", 2)) { // ASCII value - buf += (char)atoi(&token[2]); - } - - else { - return false; - } - } - return true; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/gbfmorph.cpp b/src/modules/filters/gbfmorph.cpp deleted file mode 100644 index 996baf9..0000000 --- a/src/modules/filters/gbfmorph.cpp +++ /dev/null @@ -1,82 +0,0 @@ -/****************************************************************************** - * - * gbfmorph - SWFilter descendant to hide or show morph tags - * in a GBF module. - */ - - -#include -#include -#ifndef __GNUC__ -#else -#include -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Morphological Tags"; -const char oTip[] = "Toggles Morphological Tags On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -GBFMorph::GBFMorph() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -GBFMorph::~GBFMorph() { -} - - -char GBFMorph::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - if (!option) { // if we don't want morph tags - const char *from; - char token[2048]; // cheese. Fix. - int tokpos = 0; - bool intoken = false; - int len; - bool lastspace = false; - - SWBuf orig = text; - from = orig.c_str(); - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - if (*token == 'W' && token[1] == 'T') { // Morph - if ((from[1] == ' ') || (from[1] == ',') || (from[1] == ';') || (from[1] == '.') || (from[1] == '?') || (from[1] == '!') || (from[1] == ')') || (from[1] == '\'') || (from[1] == '\"')) { - if (lastspace) - text--; - } - continue; - } - // if not a morph tag token, keep token in text - text += '<'; - text += token; - text += '>'; - continue; - } - if (intoken) { - if (tokpos < 2045) - token[tokpos++] = *from; - token[tokpos+2] = 0; - } - else { - text += *from; - lastspace = (*from == ' '); - } - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/gbfosis.cpp b/src/modules/filters/gbfosis.cpp deleted file mode 100644 index b5dd8e1..0000000 --- a/src/modules/filters/gbfosis.cpp +++ /dev/null @@ -1,439 +0,0 @@ -/****************************************************************************** - * - * gbfstrongs - SWFilter descendant to hide or show strongs number - * in a GBF module. - */ - - -#include -#include -#include -#include -#include -#include -#include -#include -#ifndef __GNUC__ -#else -#include -#endif - -SWORD_NAMESPACE_START - -GBFOSIS::GBFOSIS() { -} - - -GBFOSIS::~GBFOSIS() { -} - - -char GBFOSIS::processText(SWBuf &text, const SWKey *key, const SWModule *module) { -/* - char *to, *from, token[2048]; // cheese. Fix. - int tokpos = 0; - bool intoken = false; - int len; - bool lastspace = false; - int word = 1; - char val[128]; - char buf[128]; - char wordstr[5]; - char *valto; - char *ch; - char *textStart, *textEnd; - char *wordStart, *wordEnd; - char *fromStart; - bool newText = false; - bool newWord = false; - SWBuf tmp; - bool suspendTextPassThru = false; - bool keepToken = false; - bool handled = false; - - len = strlen(text) + 1; // shift string to right of buffer - if (len < maxlen) { - memmove(&text[maxlen - len], text, len); - from = &text[maxlen - len]; - } - else from = text; - - textStart = from; - fromStart = from; - wordStart = text; - - static QuoteStack quoteStack; - - // ------------------------------- - - for (to = text; *from; from++) { - if (*from == '<') { - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - textEnd = from-1; - wordEnd = to; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - keepToken = false; - suspendTextPassThru = false; - newWord = true; - handled = false; - - while (wordStart < (text+maxlen)) { -// if (strchr(" ,;.?!()'\"", *wordStart)) - if (strchr(";, .:?!()'\"", *wordStart) && wordStart[0] && wordStart[1]) - wordStart++; - else break; - } - while (wordEnd > wordStart) { - if (strchr(" ,;.:?!()'\"", *wordEnd)) - wordEnd--; - else break; - } - - // Scripture Reference - if (!strncmp(token, "scripRef", 8)) { - // pushString(buf, ""); - newText = true; - lastspace = false; - handled = true; - } - else if (!strcmp(token, "Rf")) { - pushString(&to, ""); - lastspace = false; - handled = true; - } - // hebrew titles - if (!strcmp(token, "TH")) { - pushString(&to, ""); - newText = true; - lastspace = false; - handled = true; - } - else if (!strcmp(token, "Th")) { - pushString(&to, ""); - lastspace = false; - handled = true; - } - // Italics assume transchange - if (!strcmp(token, "FI")) { - pushString(&to, ""); - newText = true; - lastspace = false; - handled = true; - } - else if (!strcmp(token, "Fi")) { - pushString(&to, ""); - lastspace = false; - handled = true; - } - // Paragraph break. For now use empty paragraph element - if (!strcmp(token, "CM")) { - pushString(&to, ""); - newText = true; - lastspace = false; - handled = true; - } - - // Figure - else if (!strncmp(token, "img ", 4)) { - const char *src = strstr(token, "src"); - if (!src) // assert we have a src attribute - continue; -// return false; - - pushString(&to, "
getConfigEntry("AbsoluteDataPath")); -// if (*((*buf)-1) == '/') -// c++; // skip '/' -// } -// end of uncomment for asolute path logic - - for (c++;((*c) && (*c != '"')); c++) - *to++ = *c; - - pushString(&to, "\" />"); - lastspace = false; - handled = true; - } - - // Strongs numbers - else if (*token == 'W' && (token[1] == 'G' || token[1] == 'H')) { // Strongs - bool divineName = false; - if (module->isProcessEntryAttributes()) { - valto = val; - for (unsigned int i = 1; ((token[i]) && (i < 150)); i++) - *valto++ = token[i]; - *valto = 0; - // normal strongs number - strstrip(val); - if (!strncmp(wordStart, ""); - char *attStart = strstr(wordStart, "lemma"); - if (attStart) { - attStart += 7; - sprintf(buf, "x-Strongs:%s|", val); - } - else { - attStart = wordStart + 3; - sprintf(buf, "lemma=\"x-Strongs:%s\" ", val); - } - wordStart[strlen(wordStart)] = '>'; - memmove(attStart+strlen(buf), attStart, (to-attStart)+1); - memcpy(attStart, buf, strlen(buf)); - to+=strlen(buf); - } - else { - if (!strcmp(val, "H03068")) { //divineName - sprintf(buf, "", val); - divineName = true; - } - else sprintf(buf, "", val); - - memmove(wordStart+strlen(buf), wordStart, (to-wordStart)+1); - memcpy(wordStart, buf, strlen(buf)); - to+=strlen(buf); - - if (divineName) { - wordStart += 12; - pushString(&to, ""); - } - else pushString(&to, ""); - - module->getEntryAttributes()["Word"][wordstr]["Strongs"] = val; - lastspace = false; - } - } - handled = true; - } - - // Morphology - else if (*token == 'W' && token[1] == 'T' && (token[2] == 'G' || token[2] == 'H')) { // Strongs - valto = val; - for (unsigned int i = 1; ((token[i]) && (i < 150)); i++) - *valto++ = token[i]; - *valto = 0; - strstrip(val); - if (!strncmp(wordStart, ""); - char *attStart = strstr(wordStart, "morph"); - if (attStart) { - attStart += 7; - sprintf(buf, "x-%s:%s|", "StrongsMorph", val); - } - else { - attStart = wordStart + 3; - sprintf(buf, "morph=\"x-%s:%s\" ", "StrongsMorph", val); - } - wordStart[strlen(wordStart)] = '>'; - memmove(attStart+strlen(buf), attStart, (to-attStart)+1); - memcpy(attStart, buf, strlen(buf)); - to+=strlen(buf); - } - else { - sprintf(buf, "", "StrongsMorph", val); - memmove(wordStart+strlen(buf), wordStart, (to-wordStart)+1); - memcpy(wordStart, buf, strlen(buf)); - to+=strlen(buf); - pushString(&to, ""); - lastspace = false; - } - handled = true; - } - - if (!keepToken) { - if (!handled) { - SWLog::systemlog->LogError("Unprocessed Token: <%s>", token); -// exit(-1); - } - if (from[1] && strchr(" ,;.:?!()'\"", from[1])) { - if (lastspace) - to--; - } - if (newText) {textStart = from+1; newText = false; } -// if (newWord) {wordStart = to; newWord = false; } - continue; - } - // if not a strongs token, keep token in text - *to++ = '<'; - for (char *tok = token; *tok; tok++) - *to++ = *tok; - *to++ = '>'; - if (newText) {textStart = to; newWord = false; } -// if (newWord) {wordStart = to; newWord = false; } - continue; - } - if (intoken) { - if ((tokpos < 2045) && ((*from != 10)&&(*from != 13))) { - token[tokpos++] = *from; - token[tokpos+2] = 0; - } - } - else { - switch (*from) { - case '\'': - case '\"': - case '`': -// quoteStack.handleQuote(fromStart, from, &to); - *to++ = *from; - from++; - break; - default: - if (newWord && (*from != ' ')) {wordStart = to; newWord = false; memset(to, 0, 10); } - if (!suspendTextPassThru) { - *to++ = *from; - lastspace = (*from == ' '); - } - } - } - } - - VerseKey *vkey = SWDYNAMIC_CAST(VerseKey, key); - if (vkey) { - char ref[254]; - if (vkey->Verse()) - sprintf(ref, "\t\t", vkey->getOSISRef()); - else *ref = 0; - if (*ref) { - memmove(text+strlen(ref), text, maxlen-strlen(ref)-1); - memcpy(text, ref, strlen(ref)); - to+=strlen(ref); - if (vkey->Verse()) { - VerseKey tmp; - tmp = *vkey; - tmp.AutoNormalize(0); - tmp.Headings(1); - sprintf(ref, ""); - pushString(&to, ref); - tmp = MAXVERSE; - if (*vkey == tmp) { - tmp.Verse(0); -// sprintf(ref, "\t
"); -// pushString(&to, ref); - tmp = MAXCHAPTER; - tmp = MAXVERSE; - if (*vkey == tmp) { - tmp.Chapter(0); - tmp.Verse(0); -// sprintf(ref, "\t
"); -// pushString(&to, ref); - if (!quoteStack.empty()) { - SWLog::systemlog->LogError("popping unclosed quote at end of book"); - quoteStack.clear(); - } - } - } - } - -// -// else if (vkey->Chapter()) { -// sprintf(ref, "\t
", vkey->getOSISRef()); -// } -// else sprintf(ref, "\t
", vkey->getOSISRef()); -// - } - } - *to++ = 0; - *to = 0; -*/ - return 0; -} - - -const char *GBFOSIS::convertToOSIS(const char *inRef, const SWKey *key) { - static SWBuf outRef; - - outRef = ""; - - VerseKey defLanguage; - ListKey verses = defLanguage.ParseVerseList(inRef, (*key), true); - const char *startFrag = inRef; - for (int i = 0; i < verses.Count(); i++) { - VerseKey *element = SWDYNAMIC_CAST(VerseKey, verses.GetElement(i)); - char buf[5120]; - char frag[800]; - if (element) { - memmove(frag, startFrag, ((const char *)element->userData - startFrag) + 1); - frag[((const char *)element->userData - startFrag) + 1] = 0; - startFrag = (const char *)element->userData + 1; - sprintf(buf, "%s", element->LowerBound().getOSISRef(), element->UpperBound().getOSISRef(), frag); - } - else { - memmove(frag, startFrag, ((const char *)verses.GetElement(i)->userData - startFrag) + 1); - frag[((const char *)verses.GetElement(i)->userData - startFrag) + 1] = 0; - startFrag = (const char *)verses.GetElement(i)->userData + 1; - sprintf(buf, "%s", VerseKey(*verses.GetElement(i)).getOSISRef(), frag); - } - outRef+=buf; - } - return outRef.c_str(); -} - - -QuoteStack::QuoteStack() { - clear(); -} - - -void QuoteStack::clear() { - while (!quotes.empty()) quotes.pop(); -} - - -QuoteStack::~QuoteStack() { - clear(); -} - - -void QuoteStack::handleQuote(char *buf, char *quotePos, SWBuf &text) { -//QuoteInstance(char startChar = '\"', char level = 1, string uniqueID = "", char continueCount = 0) { - if (!quotes.empty()) { - QuoteInstance last = quotes.top(); - if (last.startChar == *quotePos) { - text += ""; - quotes.pop(); - } - else { - quotes.push(QuoteInstance(*quotePos, last.level+1)); - quotes.top().pushStartStream(text); - } - } - else { - quotes.push(QuoteInstance(*quotePos)); - quotes.top().pushStartStream(text); - } -} - -void QuoteStack::QuoteInstance::pushStartStream(SWBuf &text) { - text.appendFormatted("", level); -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/gbfplain.cpp b/src/modules/filters/gbfplain.cpp deleted file mode 100644 index f519a25..0000000 --- a/src/modules/filters/gbfplain.cpp +++ /dev/null @@ -1,95 +0,0 @@ -/****************************************************************************** - * - * gbfplain - SWFilter descendant to strip out all GBF tags or convert to - * ASCII rendered symbols. - */ - - -#include -#include - -SWORD_NAMESPACE_START - -GBFPlain::GBFPlain() { -} - - -char GBFPlain::processText (SWBuf &text, const SWKey *key, const SWModule *module) -{ - char token[2048]; - int tokpos = 0; - bool intoken = false; - const char *from; - SWBuf orig = text; - from = orig.c_str(); - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - continue; - } - if (*from == '>') { - intoken = false; - // process desired tokens - switch (*token) { - case 'W': // Strongs - switch(token[1]) { - case 'G': // Greek - case 'H': // Hebrew - case 'T': // Tense - text += " <"; - for (char *tok = token + 2; *tok; tok++) - text += *tok; - text += "> "; - continue; - } - break; - case 'R': - switch(token[1]) { - case 'F': // footnote begin - text += " ["; - continue; - case 'f': // footnote end - text += "] "; - continue; - } - break; - case 'C': - switch(token[1]) { - case 'A': // ASCII value - text += (char)atoi(&token[2]); - continue; - case 'G': - text += ">"; - continue; -/* Bug in WEB - case 'L': - *to++ = '<'; - continue; -*/ - case 'L': // Bug in WEB. Use above entry when fixed - case 'N': // new line - text += '\n'; - continue; - case 'M': // new paragraph - text += "\n\n"; - continue; - } - break; - } - continue; - } - if (intoken) { - if (tokpos < 2045) - token[tokpos++] = *from; - token[tokpos+2] = 0; - } - else text += *from; - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/gbfredletterwords.cpp b/src/modules/filters/gbfredletterwords.cpp deleted file mode 100644 index df7438d..0000000 --- a/src/modules/filters/gbfredletterwords.cpp +++ /dev/null @@ -1,98 +0,0 @@ -/****************************************************************************** - * - * GBFRedLetterWords - SWFilter descendant to toggle red coloring of words of - * Christ in a GBF module. - */ - - -#include -#include -#include -#ifndef __GNUC__ -#else -#include -#endif -#include - -SWORD_NAMESPACE_START - -const char oName[] = "Words of Christ in Red"; -const char oTip[] = "Toggles Red Coloring for Words of Christ On and Off if they are marked"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -GBFRedLetterWords::GBFRedLetterWords() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -GBFRedLetterWords::~GBFRedLetterWords() { -} - - -char GBFRedLetterWords::processText(SWBuf &text, const SWKey *key, const SWModule *module) { -/** This function removes the red letter words in Bible like the WEB -* The words are marked by as start and as end tag. -*/ - if (!option) { // if we don't want footnotes - char token[4096]; // cheese. Fix. - int tokpos = 0; - bool intoken = false; - int len; - bool hide = false; - - const char *from; - SWBuf orig = text; - from = orig.c_str(); - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - tokpos = 0; -// memset(token, 0, 4096); - token[0] = 0; - token[1] = 0; - token[2] = 0; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - /*switch (*token) { - case 'F': // Font attribute - switch(token[1]) { - case 'R': // Begin red letter words - hide = true; - break; - case 'r': // end red letter words - hide = false; - break; - } - continue; // skip token - }*/ - - //hide the token if either FR or Fr was detected - hide = (token[0] == 'F' && ( (token[1] == 'R') || (token[1] == 'r') )); - - // if not a red letter word token, keep token in text - if (!hide) { - text += '<'; - for (char *tok = token; *tok; tok++) - text += *tok; - text += '>'; - } - continue; - } - if (intoken) { - if (tokpos < 4090) - token[tokpos++] = *from; - token[tokpos+2] = 0; // +2 cuz we init token with 2 extra '0' because of switch statement - } - else { - text += *from; - } - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/gbfrtf.cpp b/src/modules/filters/gbfrtf.cpp deleted file mode 100644 index 4a18fbf..0000000 --- a/src/modules/filters/gbfrtf.cpp +++ /dev/null @@ -1,289 +0,0 @@ -/****************************************************************************** - * - * gbfrtf - SWFilter descendant to convert all GBF tags to RTF tags - */ - - -#include -#include - -SWORD_NAMESPACE_START - -GBFRTF::GBFRTF() { -} - - -char GBFRTF::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - char token[2048]; - char val[128]; - char *valto; - char *num; - int tokpos = 0; - bool intoken = false; - int len; - const char *tok; - SWBuf strongnum; - SWBuf strongtense; - bool hideText = false; - int wordLen = 0; - int wordCount = 0; - int i; - - const char *from; - SWBuf orig = text; - from = orig.c_str(); - for (text = ""; *from; from++) { - if (*from == '<') { - wordLen = wordCount; - wordCount = 0; - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - continue; - } - if (*from == '>') { - intoken = false; - // process desired tokens - // deal with OSIS note tags. Just hide till OSISRTF - if (!strncmp(token, "note ", 5)) { - hideText = true; - } - if (!strncmp(token, "/note", 5)) { - hideText = false; - } - - switch (*token) { - case 'w': // OSIS Word (temporary until OSISRTF is done) - strongnum = ""; - strongtense = ""; - valto = val; - num = strstr(token, "lemma=\"x-Strongs:"); - if (num) { - for (num+=17; ((*num) && (*num != '\"')); num++) - *valto++ = *num; - *valto = 0; - if (atoi((!isdigit(*val))?val+1:val) < 5627) { - // normal strongs number - strongnum += "{\\cf3 \\sub <"; - for (tok = (!isdigit(*val))?val+1:val; *tok; tok++) - strongnum += *tok; - strongnum += ">}"; - } - /* forget these for now - else { - // verb morph - sprintf(wordstr, "%03d", word-1); - module->getEntryAttributes()["Word"][wordstr]["Morph"] = val; - } - */ - } - valto = val; - num = strstr(token, "morph=\"x-Robinson:"); - if (num) { - for (num+=18; ((*num) && (*num != '\"')); num++) - *valto++ = *num; - *valto = 0; - // normal robinsons tense - strongtense += "{\\cf4 \\sub ("; - for (tok = val; *tok; tok++) - strongtense += *tok; - strongtense += ")}"; - } - continue; - - case '/': - if (token[1] == 'w') { - if ((wordCount > 0) || (strongnum != "{\\cf3 \\sub <3588>}")) { - //for (i = 0; i < strongnum.length(); i++) - text += strongnum; - //for (i = 0; i < strongtense.length(); i++) - text += strongtense; - } - } - continue; - - case 'W': // Strongs - switch(token[1]) { - case 'G': // Greek - case 'H': // Hebrew - text += "{\\cf3 \\sub <"; - for (tok = token + 2; *tok; tok++) - text += *tok; - text += ">}"; - continue; - - case 'T': // Tense - text += "{\\cf4 \\sub ("; - bool separate = false; - for (tok = token + 2; *tok; tok++) { - if (separate) { - text += "; "; - separate = false; - } - switch (*tok) { - case 'G': - case 'H': - for (tok++; *tok; tok++) { - if (isdigit(*tok)) { - text += *tok; - separate = true; - } - else { - tok--; - break; - } - } - break; - default: - for (; *tok; tok++) { - text += *tok; - } - } - } - text += ")}"; - continue; - } - break; - case 'R': - switch(token[1]) { - case 'X': - text += ""; - continue; - case 'x': - text += ""; - continue; - case 'F': // footnote begin - text += "{\\i1 \\sub ("; - continue; - case 'f': // footnote end - text += ") }"; - continue; - } - break; - case 'F': // font tags - switch(token[1]) { - case 'I': // italic start - text += "\\i1 "; - continue; - case 'i': // italic end - text += "\\i0 "; - continue; - case 'B': // bold start - text += "\\b1 "; - continue; - case 'b': // bold end - text += "\\b0 "; - continue; - case 'N': - text += '{'; - if (!strnicmp(token+2, "Symbol", 6)) - text += "\\f7 "; - if (!strnicmp(token+2, "Courier", 7)) - text += "\\f8 "; - continue; - case 'n': - text += '}'; - continue; - case 'S': - text += "{\\super "; - continue; - case 's': - text += '}'; - continue; - case 'R': - text += "{\\cf6 "; - continue; - case 'r': - text += '}'; - continue; - case 'O': - case 'C': - text += "\\scaps1 "; - continue; - case 'o': - case 'c': - text += "\\scaps0 "; - continue; - case 'V': - text += "{\\sub "; - continue; - case 'v': - text += '}'; - continue; - case 'U': - text += "\\ul1 "; - continue; - case 'u': - text += "\\ul0 "; - continue; - } - break; - case 'C': // special character tags - switch(token[1]) { - case 'A': // ASCII value - text += (char)atoi(&token[2]); - continue; - case 'G': - text += '>'; - continue; - case 'L': // line break - text += "\\line "; - continue; - case 'M': // new paragraph - text += "\\par "; - continue; - case 'T': - text += '<'; - } - break; - case 'T': // title formatting - switch(token[1]) - { - case 'T': // Book title begin - text += "{\\large "; - continue; - case 't': - text += '}'; - continue; - case 'S': - text += "\\par {\\i1\\b1 "; - continue; - case 's': - text += "}\\par "; - continue; - } - break; - case 'J': // Strongs - switch(token[1]) { - case 'L': - text += "\\ql "; - case 'C': - text += "\\qc "; - case 'R': - text += "\\qr "; - case 'F': - text += "\\qj "; - } - } - continue; - } - if (intoken) { - if (tokpos < 2045) - token[tokpos++] = *from; - token[tokpos+2] = 0; - } - else { - if (!hideText) { - wordCount++; - text += *from; - } - } - } - return 0; -} - -SWORD_NAMESPACE_END - diff --git a/src/modules/filters/gbfstrongs.cpp b/src/modules/filters/gbfstrongs.cpp deleted file mode 100644 index bd5088a..0000000 --- a/src/modules/filters/gbfstrongs.cpp +++ /dev/null @@ -1,116 +0,0 @@ -/****************************************************************************** - * - * gbfstrongs - SWFilter descendant to hide or show strongs number - * in a GBF module. - */ - - -#include -#include -#include -#ifndef __GNUC__ -#else -#include -#endif -#include - -SWORD_NAMESPACE_START - -const char oName[] = "Strong's Numbers"; -const char oTip[] = "Toggles Strong's Numbers On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -GBFStrongs::GBFStrongs() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -GBFStrongs::~GBFStrongs() { -} - - -char GBFStrongs::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - char token[2048]; // cheese. Fix. - int tokpos = 0; - bool intoken = false; - int len; - bool lastspace = false; - int word = 1; - char val[128]; - char wordstr[5]; - char *valto; - char *ch; - unsigned int textStart = 0, textEnd = 0; - bool newText = false; - SWBuf tmp; - const char *from; - - SWBuf orig = text; - from = orig.c_str(); - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - textEnd = text.size(); - continue; - } - if (*from == '>') { // process tokens - intoken = false; - - if (*token == 'W' && (token[1] == 'G' || token[1] == 'H')) { // Strongs - if (module->isProcessEntryAttributes()) { - valto = val; - for (unsigned int i = 2; ((token[i]) && (i < 150)); i++) - *valto++ = token[i]; - *valto = 0; - if (atoi((!isdigit(*val))?val+1:val) < 5627) { - // normal strongs number - sprintf(wordstr, "%03d", word++); - module->getEntryAttributes()["Word"][wordstr]["Strongs"] = val; - tmp = ""; - tmp.append(text.c_str()+textStart, (int)(textEnd - textStart)); - module->getEntryAttributes()["Word"][wordstr]["Text"] = tmp; - newText = true; - } - else { - // verb morph - sprintf(wordstr, "%03d", word-1); - module->getEntryAttributes()["Word"][wordstr]["Morph"] = val; - } - } - if (!option) { - if ((from[1] == ' ') || (from[1] == ',') || (from[1] == ';') || (from[1] == '.') || (from[1] == '?') || (from[1] == '!') || (from[1] == ')') || (from[1] == '\'') || (from[1] == '\"')) { - if (lastspace) - text--; - } - if (newText) {textStart = text.size(); newText = false; } - continue; - } - } - // if not a strongs token, keep token in text - text += '<'; - text += token; - text += '>'; - if (newText) {textStart = text.size(); newText = false; } - continue; - } - if (intoken) { - if (tokpos < 2045) - token[tokpos++] = *from; - token[tokpos+2] = 0; - } - else { - text += *from; - lastspace = (*from == ' '); - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/gbfthml.cpp b/src/modules/filters/gbfthml.cpp deleted file mode 100644 index 03b8d8a..0000000 --- a/src/modules/filters/gbfthml.cpp +++ /dev/null @@ -1,216 +0,0 @@ -/*************************************************************************** - gbfthml.cpp - GBF to ThML filter - ------------------- - begin : 1999-10-27 - copyright : 2001 by CrossWire Bible Society - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include -#include - -SWORD_NAMESPACE_START - -GBFThML::GBFThML() -{ -} - - -char GBFThML::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - const char *from; - char token[2048]; - int tokpos = 0; - bool intoken = false; - int len; - const char *tok; - - SWBuf orig = text; - from = orig.c_str(); - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - continue; - } - if (*from == '>') - { - intoken = false; - // process desired tokens - switch (*token) { - case 'W': // Strongs - switch(token[1]) { - case 'G': - case 'H': - text += ""; - continue; - - case 'T': // Tense - text += ""; - continue; - } - break; - case 'R': - switch(token[1]) - { - case 'X': - text += ""; - continue; - case 'x': - text += ""; - continue; - case 'F': // footnote begin - text += ""; - continue; - case 'f': // footnote end - text += ""; - continue; - } - break; - case 'F': // font tags - switch(token[1]) - { - case 'N': - text += ""; - continue; - case 'n': - text += ""; - continue; - case 'I': // italic start - text += ""; - continue; - case 'i': // italic end - text += ""; - continue; - case 'B': // bold start - text += ""; - continue; - case 'b': // bold end - text += ""; - continue; - - case 'R': // words of Jesus begin - text += ""; - continue; - case 'r': // words of Jesus end - text += ""; - continue; - case 'U': // Underline start - text += ""; - continue; - case 'u': // Underline end - text += ""; - continue; - case 'O': // Old Testament quote begin - text += ""; - continue; - case 'o': // Old Testament quote end - text += ""; - continue; - case 'S': // Superscript begin - text += ""; - continue; - case 's': // Superscript end - text += ""; - continue; - case 'V': // Subscript begin - text += ""; - continue; - case 'v': // Subscript end - text += ""; - continue; - } - break; - case 'C': // special character tags - switch(token[1]) - { - case 'A': // ASCII value - text += (char)atoi(&token[2]); - continue; - case 'G': - //*to++ = ' '; - continue; - case 'L': // line break - text += "
"; - continue; - case 'M': // new paragraph - text += "

"; - continue; - case 'T': - //*to++ = ' '; - continue; - } - break; - case 'T': // title formatting - switch(token[1]) - { - case 'T': // Book title begin - text += ""; - continue; - case 't': - text += ""; - continue; - case 'S': - text += "

"; - continue; - case 's': - text += "
"; - continue; - } - break; - - case 'P': // special formatting - switch(token[1]) { - case 'P': // Poetry begin - text += ""; - continue; - case 'p': - text += ""; - continue; - } - break; - } - continue; - } - if (intoken) { - if (tokpos < 2045) - token[tokpos++] = *from; - token[tokpos+2] = 0; - } - else text += *from; - } - return 0; -} - - - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/gbfwebif.cpp b/src/modules/filters/gbfwebif.cpp deleted file mode 100644 index 131f359..0000000 --- a/src/modules/filters/gbfwebif.cpp +++ /dev/null @@ -1,161 +0,0 @@ -/*************************************************************************** - GBFWEBIF.cpp - GBF to HTML filter with hrefs - for strongs and morph tags - ------------------- - begin : 2001-09-03 - copyright : 2001 by CrossWire Bible Society - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include -#include -#include - -SWORD_NAMESPACE_START - -GBFWEBIF::GBFWEBIF() : baseURL(""), passageStudyURL(baseURL + "passagestudy.jsp") { -//all is done in GBFHTMLHREF since it inherits form this class - addTokenSubstitute("FR", ""); // words of Jesus begin - addTokenSubstitute("Fr", ""); -} - -bool GBFWEBIF::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) { - const char *tok; - char val[128]; - char *valto; - const char *num; - SWBuf url; - - if (!substituteToken(buf, token)) { - if (!strncmp(token, "w", 1)) { - // OSIS Word (temporary until OSISRTF is done) - valto = val; - num = strstr(token, "lemma=\"x-Strongs:"); - - if (num) { - for (num+=17; ((*num) && (*num != '\"')); num++) - *valto++ = *num; - *valto = 0; - - if (atoi((!isdigit(*val))?val+1:val) < 5627) { - buf += " <"; - url = ""; - for (tok = val; *tok; tok++) { - url += *tok; - } - if ((url.length() > 1) && strchr("GH", url[0])) { - if (isdigit(url[1])) - url = url.c_str()+1; - } - buf.appendFormatted("", passageStudyURL.c_str(), encodeURL(url).c_str()); - - for (tok = (!isdigit(*val))?val+1:val; *tok; tok++) { - buf += *tok; - } - buf += "> "; - } - } - valto = val; - num = strstr(token, "morph=\"x-Robinson:"); - if (num) { - for (num+=18; ((*num) && (*num != '\"')); num++) - *valto++ = *num; - *valto = 0; - buf += " ("; - url = ""; - for (tok = val; *tok; tok++) { - // normal robinsons tense - buf += *tok; - } - buf.appendFormatted("", passageStudyURL.c_str(), encodeURL(url).c_str()); - - for (tok = val; *tok; tok++) { - buf += *tok; - } - buf += ") "; - } - } - - else if (!strncmp(token, "WG", 2) || !strncmp(token, "WH", 2)) { // strong's numbers - buf += " <"; - url = ""; - - for (tok = token+1; *tok; tok++) { - url += *tok; - } - if ((url.length() > 1) && strchr("GH", url[0])) { - if (isdigit(url[1])) - url = url.c_str()+1; - } - buf.appendFormatted("", passageStudyURL.c_str(), encodeURL(url).c_str()); - - for (tok = token + 2; *tok; tok++) { - buf += *tok; - } - buf += ">"; - } - - else if (!strncmp(token, "WTG", 3) || !strncmp(token, "WTH", 3)) { // strong's numbers tense - buf += " ("; - url = ""; - for (tok = token + 2; *tok; tok++) { - if(*tok != '\"') - url += *tok; - } - if ((url.length() > 1) && strchr("GH", url[0])) { - if (isdigit(url[1])) - url = url.c_str()+1; - } - buf.appendFormatted("", passageStudyURL.c_str(), encodeURL(url).c_str()); - - for (tok = token + 3; *tok; tok++) - if(*tok != '\"') - buf += *tok; - buf += ")"; - } - - else if (!strncmp(token, "WT", 2) && strncmp(token, "WTH", 3) && strncmp(token, "WTG", 3)) { // morph tags - buf += " ("; - for (tok = token + 2; *tok; tok++) { - if(*tok != '\"') - buf += *tok; - } - buf.appendFormatted("", passageStudyURL.c_str(), encodeURL(url).c_str()); - - for (tok = token + 2; *tok; tok++) { - if(*tok != '\"') - buf += *tok; - } - buf += ")"; - } - - else if (!strncmp(token, "RX", 2)) { - buf += "", passageStudyURL.c_str(), encodeURL(url).c_str()); - } - - else { - return GBFHTMLHREF::handleToken(buf, token, userData); - } - } - return true; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/greeklexattribs.cpp b/src/modules/filters/greeklexattribs.cpp deleted file mode 100644 index 073ba39..0000000 --- a/src/modules/filters/greeklexattribs.cpp +++ /dev/null @@ -1,100 +0,0 @@ -/****************************************************************************** - * - * greeklexattribs - SWFilter descendant to set entry attributes for greek - * lexicons - */ - - -#include -#include -#include -#include -#include - -using std::string; - -SWORD_NAMESPACE_START - -GreekLexAttribs::GreekLexAttribs() { -} - - -char GreekLexAttribs::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - - if (module->isProcessEntryAttributes()) { - const char *from; - bool inAV = false; - string phrase; - string freq; - char val[128], *valto; - char wordstr[7]; - const char *currentPhrase = 0, *ch = 0; - const char *currentPhraseEnd = 0; - int number = 0; - - - for (from = text.c_str(); *from; from++) { - if (inAV) { - if (currentPhrase == 0) { - if (isalpha(*from)) - currentPhrase = from; - } - else { - if ((!isalpha(*from)) && (*from != ' ') && (*from != '+') && (*from !='(') && (*from != ')') && (*from != '\'')) { - if (*from == '<') { - if (!currentPhraseEnd) - currentPhraseEnd = from - 1; - for (; *from && *from != '>'; from++) { - if (!strncmp(from, "value=\"", 7)) { - valto = val; - from += 7; - for (unsigned int i = 0; from[i] != '\"' && i < 127; i++) - *valto++ = from[i]; - *valto = 0; - sprintf(wordstr, "%03d", number+1); - module->getEntryAttributes()["AVPhrase"][wordstr]["CompoundedWith"] = val; - from += strlen(val); - } - } - continue; - } - - phrase = ""; - phrase.append(currentPhrase, (int)(((currentPhraseEnd>currentPhrase)?currentPhraseEnd:from) - currentPhrase)-1); - currentPhrase = from; - while (*from && isdigit(*from)) from++; - freq = ""; - freq.append(currentPhrase, (int)(from - currentPhrase)); - if ((freq.length() > 0) && (phrase.length() > 0)) { - sprintf(wordstr, "%03d", ++number); - if ((strchr(phrase.c_str(), '(') > phrase.c_str()) && (strchr(phrase.c_str(), ')') > phrase.c_str() + 1)) { - string tmp = phrase.substr(0, phrase.find_first_of("(")); - phrase.erase(phrase.find_first_of("("), 1); - phrase.erase(phrase.find_first_of(")"), 1); - phrase.erase(0,phrase.find_first_not_of("\r\n\v\t ")); phrase.erase(phrase.find_last_not_of("\r\n\v\t ")+1); - module->getEntryAttributes()["AVPhrase"][wordstr]["Alt"] = phrase.c_str(); - phrase = tmp; - } - phrase.erase(0,phrase.find_first_not_of("\r\n\v\t ")); phrase.erase(phrase.find_last_not_of("\r\n\v\t ")+1); - freq.erase(0,freq.find_first_not_of("\r\n\v\t ")); freq.erase(freq.find_last_not_of("\r\n\v\t ")+1); - module->getEntryAttributes()["AVPhrase"][wordstr]["Phrase"] = phrase.c_str(); - module->getEntryAttributes()["AVPhrase"][wordstr]["Frequency"] = freq.c_str(); - currentPhrase = 0; - currentPhraseEnd = 0; - } - } - } - if (*from == ';') inAV = false; - - } - else if (!strncmp(from, "AV-", 3)) { - inAV = true; - from+=2; - } - } - } - return 0; -} - - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/latin1utf16.cpp b/src/modules/filters/latin1utf16.cpp deleted file mode 100644 index 8067381..0000000 --- a/src/modules/filters/latin1utf16.cpp +++ /dev/null @@ -1,119 +0,0 @@ -/****************************************************************************** - * - * Latin1UTF16 - SWFilter descendant to convert a Latin-1 character to UTF-16 - * - */ - - -#include -#include -#include - -SWORD_NAMESPACE_START - -Latin1UTF16::Latin1UTF16() { -} - - -char Latin1UTF16::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - const unsigned char *from; - int len; - if ((unsigned long)key < 2) // hack, we're en(1)/de(0)ciphering - return -1; - - - SWBuf orig = text; - from = (const unsigned char *)orig.c_str(); - - for (text = ""; *from; from++) { - text.setSize(text.size()+2); - switch (*from) { - case 0x80: // '€' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x20AC; - break; - case 0x82: // '‚' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x201A; - break; - case 0x83: // 'ƒ' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x0192; - break; - case 0x84: // '„' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x201E; - break; - case 0x85: // '…' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x2026; - break; - case 0x86: // '†' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x2020; - break; - case 0x87: // '‡' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x2021; - break; - case 0x88: // 'ˆ' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x02C6; - break; - case 0x89: // '‰' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x2030; - break; - case 0x8A: // 'Š' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x0160; - break; - case 0x8B: // '‹' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x2039; - break; - case 0x8C: // 'Œ' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x0152; - break; - case 0x8E: // 'Ž' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x017D; - break; - case 0x91: // '‘' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x2018; - break; - case 0x92: // '’' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x2019; - break; - case 0x93: // '“' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x201C; - break; - case 0x94: // '”' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x201D; - break; - case 0x95: // '•' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x2022; - break; - case 0x96: // '–' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x2013; - break; - case 0x97: // '—' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x2014; - break; - case 0x98: // '˜' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x02DC; - break; - case 0x99: // '™' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x2122; - break; - case 0x9A: // 'š' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x0161; - break; - case 0x9B: // '›' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x203A; - break; - case 0x9C: // 'œ' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x0153; - break; - case 0x9E: // 'ž' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x017E; - break; - case 0x9F: // 'Ÿ' - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) 0x0178; - break; - default: - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short) *from; - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/latin1utf8.cpp b/src/modules/filters/latin1utf8.cpp deleted file mode 100644 index 6d7d87b..0000000 --- a/src/modules/filters/latin1utf8.cpp +++ /dev/null @@ -1,173 +0,0 @@ -/****************************************************************************** - * - * Latin1UTF8 - SWFilter descendant to convert a Latin-1 character to UTF-8 - * - */ - - -#include -#include -#include -#include - -SWORD_NAMESPACE_START - -Latin1UTF8::Latin1UTF8() { -} - - -char Latin1UTF8::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - const unsigned char *from; - - if ((unsigned long)key < 2) // hack, we're en(1)/de(0)ciphering - return -1; - - SWBuf orig = text; - from = (const unsigned char *)orig.c_str(); - - for (text = ""; *from; from++) { - if (*from < 0x80) { - text += *from; - } - else if (*from < 0xc0) { - switch(*from) { - case 0x80: // '€' - text += 0xe2; // 'â' - text += 0x82; // '‚' - text += 0xac; // '¬' - break; - case 0x82: // '‚' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0x9a; // 'š' - break; - case 0x83: // 'ƒ' - text += 0xc6; // 'Æ' - text += 0x92; // '’' - break; - case 0x84: // '„' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0x9e; // 'ž' - break; - case 0x85: // '…' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0xa6; // '¦' - break; - case 0x86: // '†' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0xa0; // ' ' - break; - case 0x87: // '‡' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0xa1; // '¡' - break; - case 0x88: // 'ˆ' - text += 0xcb; // 'Ë' - text += 0x86; // '†' - break; - case 0x89: // '‰' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0xb0; // '°' - break; - case 0x8A: // 'Š' - text += 0xc5; // 'Å' - text += 0xa0; // ' ' - break; - case 0x8B: // '‹' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0xb9; // '¹' - break; - case 0x8C: // 'Œ' - text += 0xc5; // 'Å' - text += 0x92; // '’' - break; - case 0x8E: // 'Ž' - text += 0xc5; // 'Å' - text += 0xbd; // '½' - break; - case 0x91: // '‘' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0x98; // '˜' - break; - case 0x92: // '’' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0x99; // '™' - break; - case 0x93: // '“' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0x9c; // 'œ' - break; - case 0x94: // '”' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0x9d; // '' - break; - case 0x95: // '•' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0xa2; // '¢' - break; - case 0x96: // '–' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0x93; // '“' - break; - case 0x97: // '—' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0x94; // '”' - break; - case 0x98: // '˜' - text += 0xcb; // 'Ë' - text += 0x9c; // 'œ' - break; - case 0x99: // '™' - text += 0xe2; // 'â' - text += 0x84; // '„' - text += 0xa2; // '¢' - break; - case 0x9A: // 'š' - text += 0xc5; // 'Å' - text += 0xa1; // '¡' - break; - case 0x9B: // '›' - text += 0xe2; // 'â' - text += 0x80; // '€' - text += 0xba; // 'º' - break; - case 0x9C: // 'œ' - text += 0xc5; // 'Å' - text += 0x93; // '“' - break; - case 0x9E: // 'ž' - text += 0xc5; // 'Å' - text += 0xbe; // '¾' - break; - case 0x9F: // 'Ÿ' - text += 0xc5; // 'Å' - text += 0xb8; // '¸' - break; - default: - text += 0xC2; - text += *from; - } - } - else { - text += 0xC3; - text += (*from - 0x40); - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/osisfootnotes.cpp b/src/modules/filters/osisfootnotes.cpp deleted file mode 100644 index 59a7cae..0000000 --- a/src/modules/filters/osisfootnotes.cpp +++ /dev/null @@ -1,138 +0,0 @@ -/****************************************************************************** - * - * osisfootnotes - SWFilter descendant to hide or show footnotes - * in an OSIS module. - */ - - -#include -#include -#include -#include -#include -#include -#ifndef __GNUC__ -#else -#include -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Footnotes"; -const char oTip[] = "Toggles Footnotes On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -OSISFootnotes::OSISFootnotes() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -OSISFootnotes::~OSISFootnotes() { -} - - -char OSISFootnotes::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - SWBuf token; - bool intoken = false; - bool hide = false; - SWBuf tagText; - XMLTag startTag; - SWBuf refs = ""; - int footnoteNum = 1; - char buf[254]; - VerseKey parser = key->getText(); - - SWBuf orig = text; - const char *from = orig.c_str(); - - for (text = ""; *from; from++) { - - // remove all newlines temporarily to fix kjv2003 module - if ((*from == 10) || (*from == 13)) { - if ((text.length()>1) && (text[text.length()-2] != ' ') && (*(from+1) != ' ')) - text += ' '; - continue; - } - - - if (*from == '<') { - intoken = true; - token = ""; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - - XMLTag tag(token); - if (!strcmp(tag.getName(), "note")) { - if (!tag.isEndTag()) { - if (SWBuf("strongsMarkup") == tag.getAttribute("type")) { // handle bug in KJV2003 module where some note open tags were - tag.setEmpty(false); - } - if (!tag.isEmpty()) { -// if ((!tag.isEmpty()) || (SWBuf("strongsMarkup") == tag.getAttribute("type"))) { - refs = ""; - startTag = tag; - hide = true; - tagText = ""; - continue; - } - } - if (hide && tag.isEndTag()) { - if (module->isProcessEntryAttributes()) { - sprintf(buf, "%i", footnoteNum++); - StringList attributes = startTag.getAttributeNames(); - for (StringList::iterator it = attributes.begin(); it != attributes.end(); it++) { - module->getEntryAttributes()["Footnote"][buf][it->c_str()] = startTag.getAttribute(it->c_str()); - } - module->getEntryAttributes()["Footnote"][buf]["body"] = tagText; - startTag.setAttribute("swordFootnote", buf); - if ((startTag.getAttribute("type")) && (!strcmp(startTag.getAttribute("type"), "crossReference"))) { - if (!refs.length()) - refs = parser.ParseVerseList(tagText.c_str(), parser, true).getRangeText(); - module->getEntryAttributes()["Footnote"][buf]["refList"] = refs.c_str(); - } - } - hide = false; - if ((option) || ((startTag.getAttribute("type") && (!strcmp(startTag.getAttribute("type"), "crossReference"))))) { // we want the tag in the text; crossReferences are handled by another filter - text += startTag; - text.append(tagText); - } - else continue; - } - } - - // if not a heading token, keep token in text - if ((!strcmp(tag.getName(), "reference")) && (!tag.isEndTag())) { - SWBuf osisRef = tag.getAttribute("osisRef"); - if (refs.length()) - refs += "; "; - refs += osisRef; - } - if (!hide) { - text += '<'; - text.append(token); - text += '>'; - } - else { - tagText += '<'; - tagText.append(token); - tagText += '>'; - } - continue; - } - if (intoken) { //copy token - token += *from; - } - else if (!hide) { //copy text which is not inside a token - text += *from; - } - else tagText += *from; - } - return 0; -} - -SWORD_NAMESPACE_END - diff --git a/src/modules/filters/osisheadings.cpp b/src/modules/filters/osisheadings.cpp deleted file mode 100644 index 8ec9ce3..0000000 --- a/src/modules/filters/osisheadings.cpp +++ /dev/null @@ -1,118 +0,0 @@ -/****************************************************************************** - * - *osisheadings - SWFilter descendant to hide or show headings - * in an OSIS module. - */ - - -#include -#include -#include -#include -#ifndef __GNUC__ -#else -#include -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Headings"; -const char oTip[] = "Toggles Headings On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -OSISHeadings::OSISHeadings() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -OSISHeadings::~OSISHeadings() { -} - - -char OSISHeadings::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - SWBuf token; - bool intoken = false; - bool hide = false; - bool preverse = false; - SWBuf header; - int headerNum = 0; - int pvHeaderNum = 0; - char buf[254]; - - SWBuf orig = text; - const char *from = orig.c_str(); - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - token = ""; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - - XMLTag tag(token); - if (!stricmp(tag.getName(), "title")) { - if ((tag.getAttribute("subtype")) && (!stricmp(tag.getAttribute("subtype"), "x-preverse"))) { - hide = true; - preverse = true; - header = ""; - continue; - } - if (!tag.isEndTag()) { - hide = true; - header = ""; - if (option) { // we want the tag in the text - text += '<'; - text.append(token); - text += '>'; - } - continue; - } - if (hide && tag.isEndTag()) { - - if (module->isProcessEntryAttributes() && option) { - if (preverse) { - sprintf(buf, "%i", pvHeaderNum++); - module->getEntryAttributes()["Heading"]["Preverse"][buf] = header; - } - else { - sprintf(buf, "%i", headerNum++); - module->getEntryAttributes()["Heading"]["Interverse"][buf] = header; - if (option) { // we want the tag in the text - text.append(header); - } - } - } - hide = false; - if ((!option) || (preverse)) { // we don't want the tag in the text anymore - preverse = false; - continue; - } - preverse = false; - } - } - - // if not a heading token, keep token in text - if (!hide) { - text += '<'; - text.append(token); - text += '>'; - } - continue; - } - if (intoken) { //copy token - token += *from; - } - else if (!hide) { //copy text which is not inside a token - text += *from; - } - else header += *from; - } - return 0; -} - -SWORD_NAMESPACE_END - diff --git a/src/modules/filters/osishtmlhref.cpp b/src/modules/filters/osishtmlhref.cpp deleted file mode 100644 index 26e6dff..0000000 --- a/src/modules/filters/osishtmlhref.cpp +++ /dev/null @@ -1,339 +0,0 @@ -/*************************************************************************** - osishtmlhref.cpp - OSIS to HTML with hrefs filter - ------------------- - begin : 2003-06-24 - copyright : 2003 by CrossWire Bible Society - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include -#include -#include -#include -#include - -SWORD_NAMESPACE_START - - -OSISHTMLHREF::MyUserData::MyUserData(const SWModule *module, const SWKey *key) : BasicFilterUserData(module, key) { - osisQToTick = ((!module->getConfigEntry("OSISqToTick")) || (strcmp(module->getConfigEntry("OSISqToTick"), "false"))); -} - - -OSISHTMLHREF::OSISHTMLHREF() { - setTokenStart("<"); - setTokenEnd(">"); - - setEscapeStart("&"); - setEscapeEnd(";"); - - setEscapeStringCaseSensitive(true); - - addEscapeStringSubstitute("amp", "&"); - addEscapeStringSubstitute("apos", "'"); - addEscapeStringSubstitute("lt", "<"); - addEscapeStringSubstitute("gt", ">"); - addEscapeStringSubstitute("quot", "\""); - addTokenSubstitute("lg", "
"); - addTokenSubstitute("/lg", "
"); - - setTokenCaseSensitive(true); -} - - -bool OSISHTMLHREF::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) { - // manually process if it wasn't a simple substitution - if (!substituteToken(buf, token)) { - MyUserData *u = (MyUserData *)userData; - XMLTag tag(token); - - // tag - if (!strcmp(tag.getName(), "w")) { - - // start tag - if ((!tag.isEmpty()) && (!tag.isEndTag())) { - u->w = token; - } - - // end or empty tag - else { - bool endTag = tag.isEndTag(); - SWBuf lastText; - bool show = true; // to handle unplaced article in kjv2003-- temporary till combined - - if (endTag) { - tag = u->w.c_str(); - lastText = u->lastTextNode.c_str(); - } - else lastText = "stuff"; - - const char *attrib; - const char *val; - if (attrib = tag.getAttribute("xlit")) { - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - buf.appendFormatted(" %s", val); - } - if (attrib = tag.getAttribute("gloss")) { - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - buf.appendFormatted(" %s", val); - } - if (attrib = tag.getAttribute("lemma")) { - int count = tag.getAttributePartCount("lemma"); - int i = (count > 1) ? 0 : -1; // -1 for whole value cuz it's faster, but does the same thing as 0 - do { - attrib = tag.getAttribute("lemma", i); - if (i < 0) i = 0; // to handle our -1 condition - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - const char *val2 = val; - if ((strchr("GH", *val)) && (isdigit(val[1]))) - val2++; - if ((!strcmp(val2, "3588")) && (lastText.length() < 1)) - show = false; - else buf.appendFormatted(" <%s> ", val, val2); - } while (++i < count); - } - if ((attrib = tag.getAttribute("morph")) && (show)) { - SWBuf savelemma = tag.getAttribute("savlm"); - if ((strstr(savelemma.c_str(), "3588")) && (lastText.length() < 1)) - show = false; - if (show) { - int count = tag.getAttributePartCount("morph"); - int i = (count > 1) ? 0 : -1; // -1 for whole value cuz it's faster, but does the same thing as 0 - do { - attrib = tag.getAttribute("morph", i); - if (i < 0) i = 0; // to handle our -1 condition - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - const char *val2 = val; - if ((*val == 'T') && (strchr("GH", val[1])) && (isdigit(val[2]))) - val2+=2; - buf.appendFormatted(" (%s) ", tag.getAttribute("morph"), val, val2); - } while (++i < count); - } - } - if (attrib = tag.getAttribute("POS")) { - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - buf.appendFormatted(" %s", val); - } - - /*if (endTag) - buf += "}";*/ - } - } - - // tag - else if (!strcmp(tag.getName(), "note")) { - if (!tag.isEndTag()) { - if (!tag.isEmpty()) { - SWBuf type = tag.getAttribute("type"); - - if (type != "strongsMarkup") { // leave strong's markup notes out, in the future we'll probably have different option filters to turn different note types on or off - SWBuf footnoteNumber = tag.getAttribute("swordFootnote"); - VerseKey *vkey; - // see if we have a VerseKey * or descendant - try { - vkey = SWDYNAMIC_CAST(VerseKey, u->key); - } - catch ( ... ) { } - if (vkey) { - char ch = ((tag.getAttribute("type") && ((!strcmp(tag.getAttribute("type"), "crossReference")) || (!strcmp(tag.getAttribute("type"), "x-cross-ref")))) ? 'x':'n'); - buf.appendFormatted("*%c ", vkey->getText(), ch, footnoteNumber.c_str(), ch); - } - } - u->suspendTextPassThru = true; - } - } - if (tag.isEndTag()) { - u->suspendTextPassThru = false; - } - } - - //

paragraph tag - else if (!strcmp(tag.getName(), "p")) { - if ((!tag.isEndTag()) && (!tag.isEmpty())) { // non-empty start tag - buf += "
"; - } - else if (tag.isEndTag()) { // end tag - buf += "
"; - userData->supressAdjacentWhitespace = true; - } - else { // empty paragraph break marker - buf += "
"; - userData->supressAdjacentWhitespace = true; - } - } - - // tag - else if (!strcmp(tag.getName(), "reference")) { - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - buf += ""; - } - else if (tag.isEndTag()) { - buf += ""; - } - } - - // poetry, etc - else if (!strcmp(tag.getName(), "l")) { - if (tag.isEmpty()) { - buf += "
"; - } - else if (tag.isEndTag()) { - buf += "
"; - } - else if (tag.getAttribute("sID")) { // empty line marker - buf += "
"; - } - } - - // - else if ((!strcmp(tag.getName(), "milestone")) && (tag.getAttribute("type")) && (!strcmp(tag.getAttribute("type"), "line"))) { - buf += "
"; - userData->supressAdjacentWhitespace = true; - } - - // - else if (!strcmp(tag.getName(), "title")) { - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - buf += "<b>"; - } - else if (tag.isEndTag()) { - buf += "</b><br />"; - } - } - - // <hi> hi? hi contrast? - else if (!strcmp(tag.getName(), "hi")) { - SWBuf type = tag.getAttribute("type"); - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - if (type == "b" || type == "x-b") { - buf += "<b> "; - u->inBold = true; - } - else { // all other types - buf += "<i> "; - u->inBold = false; - } - } - else if (tag.isEndTag()) { - if(u->inBold) { - buf += "</b>"; - u->inBold = false; - } - else - buf += "</i>"; - } - else { // empty hi marker - // what to do? is this even valid? - } - } - - // <q> quote - else if (!strcmp(tag.getName(), "q")) { - SWBuf type = tag.getAttribute("type"); - SWBuf who = tag.getAttribute("who"); - const char *lev = tag.getAttribute("level"); - int level = (lev) ? atoi(lev) : 1; - - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - /*buf += "{";*/ - - //alternate " and ' - if (u->osisQToTick) - buf += (level % 2) ? '\"' : '\''; - - if (who == "Jesus") { - buf += "<font color=\"red\"> "; - } - } - else if (tag.isEndTag()) { - //alternate " and ' - if (u->osisQToTick) - buf += (level % 2) ? '\"' : '\''; - //buf += "</font>"; - } - else { // empty quote marker - //alternate " and ' - if (u->osisQToTick) - buf += (level % 2) ? '\"' : '\''; - } - } - - // <transChange> - else if (!strcmp(tag.getName(), "transChange")) { - SWBuf type = tag.getAttribute("type"); - - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - -// just do all transChange tags this way for now -// if (type == "supplied") - buf += "<i>"; - } - else if (tag.isEndTag()) { - buf += "</i>"; - } - else { // empty transChange marker? - } - } - - // image - else if (!strcmp(tag.getName(), "figure")) { - const char *src = tag.getAttribute("src"); - if (!src) // assert we have a src attribute - return false; - - char* filepath = new char[strlen(u->module->getConfigEntry("AbsoluteDataPath")) + strlen(token)]; - *filepath = 0; - strcpy(filepath, userData->module->getConfigEntry("AbsoluteDataPath")); - strcat(filepath, src); - -// we do this because BibleCS looks for this EXACT format for an image tag - buf+="<image src=\""; - buf+=filepath; - buf+="\" />"; -/* - char imgc; - for (c = filepath + strlen(filepath); c > filepath && *c != '.'; c--); - c++; - FILE* imgfile; - if (stricmp(c, "jpg") || stricmp(c, "jpeg")) { - imgfile = fopen(filepath, "r"); - if (imgfile != NULL) { - buf += "{\\nonshppict {\\pict\\jpegblip "; - while (feof(imgfile) != EOF) { - buf.appendFormatted("%2x", fgetc(imgfile)); - } - fclose(imgfile); - buf += "}}"; - } - } - else if (stricmp(c, "png")) { - buf += "{\\*\\shppict {\\pict\\pngblip "; - - buf += "}}"; - } -*/ - delete [] filepath; - } - - else { - return false; // we still didn't handle token - } - } - return true; -} - - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/osislemma.cpp b/src/modules/filters/osislemma.cpp deleted file mode 100644 index e31c002..0000000 --- a/src/modules/filters/osislemma.cpp +++ /dev/null @@ -1,78 +0,0 @@ -/****************************************************************************** - * - * osislemma - SWFilter descendant to hide or show lemmata - * in a OSIS module. - */ - - -#include <stdlib.h> -#include <osislemma.h> -#include <utilxml.h> -#ifndef __GNUC__ -#else -#include <unixstr.h> -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Lemmas"; -const char oTip[] = "Toggles Lemmas On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -OSISLemma::OSISLemma() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -OSISLemma::~OSISLemma() { -} - - -char OSISLemma::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - if (!option) { // if we don't want lemmas - const char *from; - char token[2048]; // cheese. Fix. - int tokpos = 0; - bool intoken = false; - bool lastspace = false; - SWBuf orig = text; - from = orig.c_str(); - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - tokpos = 0; - token[0] = 0; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - XMLTag tag(token); - if ((!strcmp(tag.getName(), "w")) && (!tag.isEndTag())) { // Lemma - SWBuf lemma = tag.getAttribute("lemma"); - if (lemma.length()) { - tag.setAttribute("lemma", 0); - tag.setAttribute("savlm", lemma.c_str()); - } - } - // keep tag, possibly with the lemma removed - text += tag; - continue; - } - if (intoken) { - if (tokpos < 2045) - token[tokpos++] = *from; - token[tokpos] = 0; - } - else { - text += *from; - lastspace = (*from == ' '); - } - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/osismorph.cpp b/src/modules/filters/osismorph.cpp deleted file mode 100644 index 1b2d116..0000000 --- a/src/modules/filters/osismorph.cpp +++ /dev/null @@ -1,75 +0,0 @@ -/****************************************************************************** - * - * osismorph - SWFilter descendant to hide or show morph tags - * in a OSIS module. - */ - - -#include <stdlib.h> -#include <osismorph.h> -#include <utilxml.h> -#ifndef __GNUC__ -#else -#include <unixstr.h> -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Morphological Tags"; -const char oTip[] = "Toggles Morphological Tags On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -OSISMorph::OSISMorph() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -OSISMorph::~OSISMorph() { -} - - -char OSISMorph::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - if (!option) { // if we don't want morph tags - const char *from; - char token[2048]; // cheese. Fix. - int tokpos = 0; - bool intoken = false; - bool lastspace = false; - SWBuf orig = text; - from = orig.c_str(); - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - tokpos = 0; - token[0] = 0; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - XMLTag tag(token); - if ((!strcmp(tag.getName(), "w")) && (!tag.isEndTag())) { // Morph - if (tag.getAttribute("morph")) - tag.setAttribute("morph", 0); - } - // keep tag, possibly with the morph removed - text += tag; - continue; - } - if (intoken) { - if (tokpos < 2045) - token[tokpos++] = *from; - token[tokpos] = 0; - } - else { - text += *from; - lastspace = (*from == ' '); - } - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/osisplain.cpp b/src/modules/filters/osisplain.cpp deleted file mode 100644 index 7a12a27..0000000 --- a/src/modules/filters/osisplain.cpp +++ /dev/null @@ -1,151 +0,0 @@ -/*************************************************************************** - osisplain.cpp - OSIS to Plaintext filter - ------------------- - begin : 2003-02-15 - copyright : 2003 by CrossWire Bible Society - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include <stdlib.h> -#include <osisplain.h> -#include <utilxml.h> -#include <ctype.h> - -SWORD_NAMESPACE_START - -OSISPlain::OSISPlain() { - setTokenStart("<"); - setTokenEnd(">"); - - setEscapeStart("&"); - setEscapeEnd(";"); - - setEscapeStringCaseSensitive(true); - - addEscapeStringSubstitute("amp", "&"); - addEscapeStringSubstitute("apos", "'"); - addEscapeStringSubstitute("lt", "<"); - addEscapeStringSubstitute("gt", ">"); - addEscapeStringSubstitute("quot", "\""); - - - addTokenSubstitute("title", "\n"); - addTokenSubstitute("/title", "\n"); - addTokenSubstitute("/l", "\n"); - addTokenSubstitute("lg", "\n"); - addTokenSubstitute("/lg", "\n"); - - setTokenCaseSensitive(true); -} - - -bool OSISPlain::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) { - // manually process if it wasn't a simple substitution - if (!substituteToken(buf, token)) { - MyUserData *u = (MyUserData *)userData; - XMLTag tag(token); - if (((*token == 'w') && (token[1] == ' ')) || - ((*token == '/') && (token[1] == 'w') && (!token[2]))) { - bool start = false; - if (*token == 'w') { - if (token[strlen(token)-1] != '/') { - u->w = token; - return true; - } - start = true; - } - tag = (start) ? token : u->w.c_str(); - bool show = true; // to handle unplaced article in kjv2003-- temporary till combined - - SWBuf lastText = (start) ? "stuff" : u->lastTextNode.c_str(); - - const char *attrib; - const char *val; - if (attrib = tag.getAttribute("xlit")) { - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - buf.appendFormatted(" <%s>", val); - } - if (attrib = tag.getAttribute("gloss")) { - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - buf.appendFormatted(" <%s>", val); - } - if (attrib = tag.getAttribute("lemma")) { - int count = tag.getAttributePartCount("lemma"); - int i = (count > 1) ? 0 : -1; // -1 for whole value cuz it's faster, but does the same thing as 0 - do { - attrib = tag.getAttribute("lemma", i); - if (i < 0) i = 0; // to handle our -1 condition - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - if ((strchr("GH", *val)) && (isdigit(val[1]))) - val++; - if ((!strcmp(val, "3588")) && (lastText.length() < 1)) - show = false; - else buf.appendFormatted(" <%s>}", val); - } while (++i < count); - } - if ((attrib = tag.getAttribute("morph")) && (show)) { - int count = tag.getAttributePartCount("morph"); - int i = (count > 1) ? 0 : -1; // -1 for whole value cuz it's faster, but does the same thing as 0 - do { - attrib = tag.getAttribute("morph", i); - if (i < 0) i = 0; // to handle our -1 condition - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - if ((*val == 'T') && (strchr("GH", val[1])) && (isdigit(val[2]))) - val+=2; - buf.appendFormatted(" (%s)", val); - } while (++i < count); - } - if (attrib = tag.getAttribute("POS")) { - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - buf.appendFormatted(" <%s>", val); - } - } - - // <note> tag - else if (!strncmp(token, "note", 4)) { - if (!strstr(token, "strongsMarkup")) { // leave strong's markup notes out, in the future we'll probably have different option filters to turn different note types on or off - buf += " ("; - } - else u->suspendTextPassThru = true; - } - else if (!strncmp(token, "/note", 5)) { - if (!u->suspendTextPassThru) - buf += ")"; - else u->suspendTextPassThru = false; - } - - // <p> paragraph tag - else if (((*token == 'p') && ((token[1] == ' ') || (!token[1]))) || - ((*token == '/') && (token[1] == 'p') && (!token[2]))) { - userData->supressAdjacentWhitespace = true; - buf += "\n"; - } - - // <milestone type="line"/> - else if ((!strcmp(tag.getName(), "milestone")) && (tag.getAttribute("type")) && (!strcmp(tag.getAttribute("type"), "line"))) { - userData->supressAdjacentWhitespace = true; - buf += "\n"; - } - - else { - return false; // we still didn't handle token - } - } - return true; -} - - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/osisredletterwords.cpp b/src/modules/filters/osisredletterwords.cpp deleted file mode 100644 index a9a4834..0000000 --- a/src/modules/filters/osisredletterwords.cpp +++ /dev/null @@ -1,77 +0,0 @@ -/****************************************************************************** - * - * OSISRedLetterWords - SWFilter descendant to toggle red coloring for words - * of Christ in an OSIS module. - */ - - -#include <stdlib.h> -#include <osisredletterwords.h> -#include <swmodule.h> -#include <utilxml.h> -#ifndef __GNUC__ -#else -#include <unixstr.h> -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Words of Christ in Red"; -const char oTip[] = "Toggles Red Coloring for Words of Christ On and Off if they are marked"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -OSISRedLetterWords::OSISRedLetterWords() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("On"); -} - - -OSISRedLetterWords::~OSISRedLetterWords() { -} - - -char OSISRedLetterWords::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - SWBuf token; - bool intoken = false; - char buf[254]; - - SWBuf orig = text; - const char *from = orig.c_str(); - - if (!option) - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - token = ""; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - - XMLTag tag(token); - if (!stricmp(tag.getName(), "q")) { - if ((tag.getAttribute("who")) && (!stricmp(tag.getAttribute("who"), "Jesus"))) { - tag.setAttribute("who", 0); - text += tag; // tag toString already has < and > - continue; - } - } - // if we haven't modified, still use original token instead of tag, so we don't reorder attribs and stuff. It doesn't really matter, but this is less intrusive to the original markup. - text += '<'; - text.append(token); - text += '>'; - continue; - } - if (intoken) { //copy token - token += *from; - } - else { //copy text which is not inside a token - text += *from; - } - } - return 0; -} - -SWORD_NAMESPACE_END - diff --git a/src/modules/filters/osisrtf.cpp b/src/modules/filters/osisrtf.cpp deleted file mode 100644 index e94e8ae..0000000 --- a/src/modules/filters/osisrtf.cpp +++ /dev/null @@ -1,333 +0,0 @@ -/*************************************************************************** - osisrtf.cpp - OSIS to RTF filter - ------------------- - begin : 2003-02-15 - copyright : 2003 by CrossWire Bible Society - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include <stdlib.h> -#include <osisrtf.h> -#include <utilxml.h> -#include <versekey.h> -#include <swmodule.h> - -SWORD_NAMESPACE_START - - -OSISRTF::MyUserData::MyUserData(const SWModule *module, const SWKey *key) : BasicFilterUserData(module, key) { - inXRefNote = false; - BiblicalText = false; - if (module) { - version = module->Name(); - BiblicalText = (!strcmp(module->Type(), "Biblical Texts")); - } - osisQToTick = ((!module->getConfigEntry("OSISqToTick")) || (strcmp(module->getConfigEntry("OSISqToTick"), "false"))); -} - - -OSISRTF::OSISRTF() { - setTokenStart("<"); - setTokenEnd(">"); - - setEscapeStart("&"); - setEscapeEnd(";"); - - setEscapeStringCaseSensitive(true); - - addEscapeStringSubstitute("amp", "&"); - addEscapeStringSubstitute("apos", "'"); - addEscapeStringSubstitute("lt", "<"); - addEscapeStringSubstitute("gt", ">"); - addEscapeStringSubstitute("quot", "\""); - addTokenSubstitute("lg", "{\\par}"); - addTokenSubstitute("/lg", "{\\par}"); - - setTokenCaseSensitive(true); -} - - -bool OSISRTF::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) { - // manually process if it wasn't a simple substitution - if (!substituteToken(buf, token)) { - MyUserData *u = (MyUserData *)userData; - XMLTag tag(token); - - // <w> tag - if (!strcmp(tag.getName(), "w")) { - - // start <w> tag - if ((!tag.isEmpty()) && (!tag.isEndTag())) { - buf += "{"; - u->w = token; - } - - // end or empty <w> tag - else { - bool endTag = tag.isEndTag(); - SWBuf lastText; - bool show = true; // to handle unplaced article in kjv2003-- temporary till combined - - if (endTag) { - tag = u->w.c_str(); - lastText = u->lastTextNode.c_str(); - } - else lastText = "stuff"; - - const char *attrib; - const char *val; - if (attrib = tag.getAttribute("xlit")) { - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - buf.appendFormatted(" {\\fs15 <%s>}", val); - } - if (attrib = tag.getAttribute("gloss")) { - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - buf.appendFormatted(" {\\fs15 <%s>}", val); - } - if (attrib = tag.getAttribute("lemma")) { - int count = tag.getAttributePartCount("lemma"); - int i = (count > 1) ? 0 : -1; // -1 for whole value cuz it's faster, but does the same thing as 0 - do { - attrib = tag.getAttribute("lemma", i); - if (i < 0) i = 0; // to handle our -1 condition - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - if ((strchr("GH", *val)) && (isdigit(val[1]))) - val++; - if ((!strcmp(val, "3588")) && (lastText.length() < 1)) - show = false; - else buf.appendFormatted(" {\\cf3 \\sub <%s>}", val); - } while (++i < count); - } - if ((attrib = tag.getAttribute("morph")) && (show)) { - SWBuf savelemma = tag.getAttribute("savlm"); - if ((strstr(savelemma.c_str(), "3588")) && (lastText.length() < 1)) - show = false; - if (show) { - int count = tag.getAttributePartCount("morph"); - int i = (count > 1) ? 0 : -1; // -1 for whole value cuz it's faster, but does the same thing as 0 - do { - attrib = tag.getAttribute("morph", i); - if (i < 0) i = 0; // to handle our -1 condition - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - if ((*val == 'T') && (strchr("GH", val[1])) && (isdigit(val[2]))) - val+=2; - buf.appendFormatted(" {\\cf4 \\sub (%s)}", val); - } while (++i < count); - } - } - if (attrib = tag.getAttribute("POS")) { - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - buf.appendFormatted(" {\\fs15 <%s>}", val); - } - - if (endTag) - buf += "}"; - } - } - - // <note> tag - else if (!strcmp(tag.getName(), "note")) { - if (!tag.isEndTag()) { - if (!tag.isEmpty()) { - SWBuf type = tag.getAttribute("type"); - - if (type != "strongsMarkup") { // leave strong's markup notes out, in the future we'll probably have different option filters to turn different note types on or off - SWBuf footnoteNumber = tag.getAttribute("swordFootnote"); - VerseKey *vkey; - // see if we have a VerseKey * or descendant - try { - vkey = SWDYNAMIC_CAST(VerseKey, u->key); - } - catch ( ... ) { } - if (vkey) { - char ch = ((!strcmp(type.c_str(), "crossReference")) || (!strcmp(type.c_str(), "x-cross-ref"))) ? 'x':'n'; - buf.appendFormatted("{\\super <a href=\"\">*%c%i.%s</a>} ", ch, vkey->Verse(), footnoteNumber.c_str()); - u->inXRefNote = (ch == 'x'); - } - } - u->suspendTextPassThru = true; - } - } - if (tag.isEndTag()) { - u->suspendTextPassThru = false; - u->inXRefNote = false; - } - } - - // <p> paragraph tag - else if (!strcmp(tag.getName(), "p")) { - if ((!tag.isEndTag()) && (!tag.isEmpty())) { // non-empty start tag - buf += "{\\par "; - } - else if (tag.isEndTag()) { // end tag - buf += "\\par}"; - userData->supressAdjacentWhitespace = true; - } - else { // empty paragraph break marker - buf += "{\\par\\par}"; - userData->supressAdjacentWhitespace = true; - } - } - - // <reference> tag - else if (!strcmp(tag.getName(), "reference")) { - if (!u->inXRefNote) { // only show these if we're not in an xref note - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - buf += "{<a href=\"\">"; - } - else if (tag.isEndTag()) { - buf += "</a>}"; - } - } - } - - // <l> poetry - else if (!strcmp(tag.getName(), "l")) { - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - buf += "{"; - } - else if (tag.isEndTag()) { - buf += "\\par}"; - } - else if (tag.getAttribute("sID")) { // empty line marker - buf += "{\\par}"; - } - } - - // <milestone type="line"/> - else if ((!strcmp(tag.getName(), "milestone")) && (tag.getAttribute("type")) && (!strcmp(tag.getAttribute("type"), "line"))) { - buf += "{\\par}"; - userData->supressAdjacentWhitespace = true; - } - - // <title> - else if (!strcmp(tag.getName(), "title")) { - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - buf += "{\\par\\i1\\b1 "; - } - else if (tag.isEndTag()) { - buf += "\\par}"; - } - } - - // <hi> - else if (!strcmp(tag.getName(), "hi")) { - SWBuf type = tag.getAttribute("type"); - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - if (type == "b" || type == "x-b") - buf += "{\\b1 "; - else // all other types - buf += "{\\i1 "; - } - else if (tag.isEndTag()) { - buf += "}"; - } - } - - // <q> quote - else if (!strcmp(tag.getName(), "q")) { - SWBuf type = tag.getAttribute("type"); - SWBuf who = tag.getAttribute("who"); - const char *lev = tag.getAttribute("level"); - int level = (lev) ? atoi(lev) : 1; - - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - buf += "{"; - - //alternate " and ' - if (u->osisQToTick) - buf += (level % 2) ? '\"' : '\''; - - if (who == "Jesus") - buf += "\\cf6 "; - } - else if (tag.isEndTag()) { - //alternate " and ' - if (u->osisQToTick) - buf += (level % 2) ? '\"' : '\''; - buf += "}"; - } - else { // empty quote marker - //alternate " and ' - if (u->osisQToTick) - buf += (level % 2) ? '\"' : '\''; - } - } - - // <transChange> - else if (!strcmp(tag.getName(), "transChange")) { - SWBuf type = tag.getAttribute("type"); - - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - -// just do all transChange tags this way for now -// if (type == "supplied") - buf += "{\\i1 "; - } - else if (tag.isEndTag()) { - buf += "}"; - } - } - - // image - else if (!strcmp(tag.getName(), "figure")) { - const char *src = tag.getAttribute("src"); - if (!src) // assert we have a src attribute - return false; - - char* filepath = new char[strlen(u->module->getConfigEntry("AbsoluteDataPath")) + strlen(token)]; - *filepath = 0; - strcpy(filepath, userData->module->getConfigEntry("AbsoluteDataPath")); - strcat(filepath, src); - -// we do this because BibleCS looks for this EXACT format for an image tag - buf+="<img src=\""; - buf+=filepath; - buf+="\" />"; -/* - char imgc; - for (c = filepath + strlen(filepath); c > filepath && *c != '.'; c--); - c++; - FILE* imgfile; - if (stricmp(c, "jpg") || stricmp(c, "jpeg")) { - imgfile = fopen(filepath, "r"); - if (imgfile != NULL) { - buf += "{\\nonshppict {\\pict\\jpegblip "; - while (feof(imgfile) != EOF) { - buf.appendFormatted("%2x", fgetc(imgfile)); - } - fclose(imgfile); - buf += "}}"; - } - } - else if (stricmp(c, "png")) { - buf += "{\\*\\shppict {\\pict\\pngblip "; - - buf += "}}"; - } -*/ - delete [] filepath; - } - else { - return false; // we still didn't handle token - } - } - return true; -} - - -SWORD_NAMESPACE_END - diff --git a/src/modules/filters/osisscripref.cpp b/src/modules/filters/osisscripref.cpp deleted file mode 100644 index 566e08a..0000000 --- a/src/modules/filters/osisscripref.cpp +++ /dev/null @@ -1,104 +0,0 @@ -/****************************************************************************** - * - * OSISScripref - SWFilter descendant to hide or show scripture references - * in an OSIS module. - */ - - -#include <stdlib.h> -#include <osisscripref.h> -#include <swmodule.h> -#include <utilxml.h> -#ifndef __GNUC__ -#else -#include <unixstr.h> -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Cross-references"; -const char oTip[] = "Toggles Scripture Cross-references On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -OSISScripref::OSISScripref() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("On"); -} - - -OSISScripref::~OSISScripref() { -} - - -char OSISScripref::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - SWBuf token; - bool intoken = false; - bool hide = false; - SWBuf tagText; - XMLTag startTag; - int tagTextNum = 1; - int footnoteNum = 1; - char buf[254]; - - SWBuf orig = text; - const char *from = orig.c_str(); - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - token = ""; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - - XMLTag tag(token); - if (!strcmp(tag.getName(), "note")) { - if (!tag.isEndTag() && (!tag.isEmpty())) { - startTag = tag; - if ((tag.getAttribute("type")) && (!strcmp(tag.getAttribute("type"), "crossReference"))) { - hide = true; - tagText = ""; - if (option) { // we want the tag in the text - text += '<'; - text.append(token); - text += '>'; - } - continue; - } - } - if (hide && tag.isEndTag()) { - hide = false; - if (option) { // we want the tag in the text - text.append(tagText); // end tag gets added further down - } - else continue; // don't let the end tag get added to the text - } - } - - // if not a heading token, keep token in text - if (!hide) { - text += '<'; - text.append(token); - text += '>'; - } - else { - tagText += '<'; - tagText.append(token); - tagText += '>'; - } - continue; - } - if (intoken) { //copy token - token += *from; - } - else if (!hide) { //copy text which is not inside a token - text += *from; - } - else tagText += *from; - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/osisstrongs.cpp b/src/modules/filters/osisstrongs.cpp deleted file mode 100644 index 7949b50..0000000 --- a/src/modules/filters/osisstrongs.cpp +++ /dev/null @@ -1,128 +0,0 @@ -/****************************************************************************** - * - * osisstrongs - SWFilter descendant to hide or show strongs number - * in a OSIS module. - */ - - -#include <stdlib.h> -#include <osisstrongs.h> -#include <swmodule.h> -#ifndef __GNUC__ -#else -#include <unixstr.h> -#endif -#include <ctype.h> - -SWORD_NAMESPACE_START - -const char oName[] = "Strong's Numbers"; -const char oTip[] = "Toggles Strong's Numbers On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - - -OSISStrongs::OSISStrongs() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -OSISStrongs::~OSISStrongs() { -} - - -char OSISStrongs::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - const char *from; - char token[2048]; // cheese. Fix. - int tokpos = 0; - bool intoken = false; - int len; - bool lastspace = false; - int word = 1; - char val[128]; - char wordstr[5]; - char *valto; - char *ch; - unsigned int textStart = 0, textEnd = 0; - bool newText = false; - SWBuf tmp; - - SWBuf orig = text; - from = orig.c_str(); - - len = strlen(text) + 1; // shift string to right of buffer - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - textEnd = text.size(); - continue; - } - if (*from == '>') { // process tokens - intoken = false; - if ((*token == 'w') && (token[1] == ' ')) { // Word - if (module->isProcessEntryAttributes()) { - valto = val; - char *num = strstr(token, "lemma=\"x-Strongs:"); - if (num) { - for (num+=17; ((*num) && (*num != '\"')); num++) - *valto++ = *num; - *valto = 0; - if (atoi((!isdigit(*val))?val+1:val) < 5627) { - // normal strongs number - sprintf(wordstr, "%03d", word++); - module->getEntryAttributes()["Word"][wordstr]["Strongs"] = val; - tmp = ""; - tmp.append(text.c_str()+textStart, (int)(textEnd - textStart)); - module->getEntryAttributes()["Word"][wordstr]["Text"] = tmp; - newText = true; - } - else { - // verb morph - sprintf(wordstr, "%03d", word-1); - module->getEntryAttributes()["Word"][wordstr]["Morph"] = val; - } - } - } - if (!option) { - char *num = strstr(token, "lemma=\"x-Strongs:"); - if (num) { - memcpy(num, "savlm", 5); -/* - for (int i = 0; i < 17; i++) - *num++ = ' '; - for (; ((*num) && (*num!='\"')); num++) - *num = ' '; - if (*num) - *num = ' '; -*/ - } - } - } - // if not a strongs token, keep token in text - text += '<'; - for (char *tok = token; *tok; tok++) - text += *tok; - text += '>'; - if (newText) {textStart = text.size(); newText = false; } - continue; - } - if (intoken) { - if (tokpos < 2045) - token[tokpos++] = *from; - token[tokpos+2] = 0; - } - else { - text += *from; - lastspace = (*from == ' '); - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/osiswebif.cpp b/src/modules/filters/osiswebif.cpp deleted file mode 100644 index f2db7b7..0000000 --- a/src/modules/filters/osiswebif.cpp +++ /dev/null @@ -1,212 +0,0 @@ -/*************************************************************************** - OSISWEBIF.cpp - OSIS to HTML filter with hrefs - for strongs and morph tags - ------------------- - begin : 2003-10-23 - copyright : 2003 by CrossWire Bible Society - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include <stdlib.h> -#include <osiswebif.h> -#include <utilxml.h> -#include <versekey.h> -#include <swmodule.h> -#include <ctype.h> - - -SWORD_NAMESPACE_START - - -OSISWEBIF::OSISWEBIF() : baseURL(""), passageStudyURL(baseURL + "passagestudy.jsp") { -} - -bool OSISWEBIF::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) { - // manually process if it wasn't a simple substitution - if (!substituteToken(buf, token)) { - MyUserData *u = (MyUserData *)userData; - XMLTag tag(token); - - // <w> tag - if (!strcmp(tag.getName(), "w")) { - - // start <w> tag - if ((!tag.isEmpty()) && (!tag.isEndTag())) { - u->w = token; - } - - // end or empty <w> tag - else { - bool endTag = tag.isEndTag(); - SWBuf lastText; - bool show = true; // to handle unplaced article in kjv2003-- temporary till combined - - if (endTag) { - tag = u->w.c_str(); - lastText = u->lastTextNode.c_str(); - } - else lastText = "stuff"; - - const char *attrib; - const char *val; - if (attrib = tag.getAttribute("xlit")) { - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - buf.appendFormatted(" %s", val); - } - if (attrib = tag.getAttribute("gloss")) { - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - buf.appendFormatted(" %s", val); - } - if (attrib = tag.getAttribute("lemma")) { - int count = tag.getAttributePartCount("lemma"); - int i = (count > 1) ? 0 : -1; // -1 for whole value cuz it's faster, but does the same thing as 0 - do { - attrib = tag.getAttribute("lemma", i); - if (i < 0) i = 0; // to handle our -1 condition - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - const char *val2 = val; - if ((strchr("GH", *val)) && (isdigit(val[1]))) - val2++; - if ((!strcmp(val2, "3588")) && (lastText.length() < 1)) - show = false; - else buf.appendFormatted(" <small><em><<a href=\"%s?showStrong=%s#cv\">%s</a>></em></small> ", passageStudyURL.c_str(), encodeURL(val2).c_str(), val2); - } while (++i < count); - } - if ((attrib = tag.getAttribute("morph")) && (show)) { - SWBuf savelemma = tag.getAttribute("savlm"); - if ((strstr(savelemma.c_str(), "3588")) && (lastText.length() < 1)) - show = false; - if (show) { - int count = tag.getAttributePartCount("morph"); - int i = (count > 1) ? 0 : -1; // -1 for whole value cuz it's faster, but does the same thing as 0 - do { - attrib = tag.getAttribute("morph", i); - if (i < 0) i = 0; // to handle our -1 condition - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - const char *val2 = val; - if ((*val == 'T') && (strchr("GH", val[1])) && (isdigit(val[2]))) - val2+=2; - buf.appendFormatted(" <small><em>(<a href=\"%s?showMorph=%s#cv\">%s</a>)</em></small> ", passageStudyURL.c_str(), encodeURL(val2).c_str(), val2); - } while (++i < count); - } - } - if (attrib = tag.getAttribute("POS")) { - val = strchr(attrib, ':'); - val = (val) ? (val + 1) : attrib; - buf.appendFormatted(" %s", val); - } - - /*if (endTag) - buf += "}";*/ - } - } - - // <note> tag - else if (!strcmp(tag.getName(), "note")) { - if (!tag.isEndTag()) { - if (!tag.isEmpty()) { - SWBuf type = tag.getAttribute("type"); - - if (type != "strongsMarkup") { // leave strong's markup notes out, in the future we'll probably have different option filters to turn different note types on or off - SWBuf footnoteNumber = tag.getAttribute("swordFootnote"); - VerseKey *vkey; - // see if we have a VerseKey * or descendant - try { - vkey = SWDYNAMIC_CAST(VerseKey, u->key); - } - catch ( ... ) { } - if (vkey) { - char ch = ((tag.getAttribute("type") && ((!strcmp(tag.getAttribute("type"), "crossReference")) || (!strcmp(tag.getAttribute("type"), "x-cross-ref")))) ? 'x':'n'); -// buf.appendFormatted("<a href=\"noteID=%s.%c.%s\"><small><sup>*%c</sup></small></a> ", vkey->getText(), ch, footnoteNumber.c_str(), ch); - } - } - u->suspendTextPassThru = true; - } - } - if (tag.isEndTag()) { - u->suspendTextPassThru = false; - } - } - // <title> - else if (!strcmp(tag.getName(), "title")) { - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - buf += "<h3>"; - } - else if (tag.isEndTag()) { - buf += "</h3>"; - } - } - - // <q> quote - else if (!strcmp(tag.getName(), "q")) { - SWBuf type = tag.getAttribute("type"); - SWBuf who = tag.getAttribute("who"); - const char *lev = tag.getAttribute("level"); - int level = (lev) ? atoi(lev) : 1; - - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - /*buf += "{";*/ - - //alternate " and ' - if (u->osisQToTick) - buf += (level % 2) ? '\"' : '\''; - - if (who == "Jesus") { - buf += "<span class=\"wordsOfJesus\"> "; - } - } - else if (tag.isEndTag()) { - //alternate " and ' - if (u->osisQToTick) - buf += (level % 2) ? '\"' : '\''; - buf += "</span>"; - } - else { // empty quote marker - //alternate " and ' - if (u->osisQToTick) - buf += (level % 2) ? '\"' : '\''; - } - } - - // <transChange> - else if (!strcmp(tag.getName(), "transChange")) { - if ((!tag.isEndTag()) && (!tag.isEmpty())) { - SWBuf type = tag.getAttribute("type"); - u->lastTransChange = type; - -// just do all transChange tags this way for now - if ((type == "added") || (type == "supplied")) - buf += "<i>"; - else if (type == "tenseChange") - buf += "*"; - } - else if (tag.isEndTag()) { - SWBuf type = u->lastTransChange; - if ((type == "added") || (type == "supplied")) - buf += "</i>"; - } - else { // empty transChange marker? - } - } - else { - return OSISHTMLHREF::handleToken(buf, token, userData); - } - } - return true; -} - - -SWORD_NAMESPACE_END - diff --git a/src/modules/filters/plainfootnotes.cpp b/src/modules/filters/plainfootnotes.cpp deleted file mode 100644 index 0ae50ef..0000000 --- a/src/modules/filters/plainfootnotes.cpp +++ /dev/null @@ -1,83 +0,0 @@ -/*************************************************************************** - plainfootnotes.cpp - description - ------------------- - begin : Wed Oct 13 1999 - copyright : (C) 1999 by The team of BibleTime - email : info@bibletime.de - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include <plainfootnotes.h> -#include <swkey.h> - -#include <stdlib.h> -#ifndef __GNUC__ -#else -#include <unixstr.h> -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Footnotes"; -const char oTip[] = "Toggles Footnotes On and Off In Bible Texts If They Exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -PLAINFootnotes::PLAINFootnotes() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - -PLAINFootnotes::~PLAINFootnotes(){ -} - - -char PLAINFootnotes::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - if (!option) { // if we don't want footnotes - //char token[2048]; - //SWBuf token; - //int tokpos = 0; - //bool intoken = false; - //bool lastspace = false; - - bool hide = false; - - SWBuf orig = text; - const char *from = orig.c_str(); - for (text = ""; *from; from++) { - if (*from == '{') // Footnote start - { - hide = true; - continue; - } - else if (*from == '}') // Footnote end - { - hide = false; - continue; - } - - //if (intoken) { - //if (tokpos < 2045) - // token += *from; - // token[tokpos+2] = 0; - //} - //else { - if (!hide) { - text = *from; - //lastspace = (*from == ' '); - } - //} - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/plainhtml.cpp b/src/modules/filters/plainhtml.cpp deleted file mode 100644 index 19f4bc2..0000000 --- a/src/modules/filters/plainhtml.cpp +++ /dev/null @@ -1,70 +0,0 @@ -/*************************************************************************** - rwphtml.cpp - description - ------------------- - begin : Thu Jun 24 1999 - copyright : (C) 1999 by Torsten Uhlmann - email : TUhlmann@gmx.de - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include <plainhtml.h> - -SWORD_NAMESPACE_START - -PLAINHTML::PLAINHTML() -{ -} - - -char PLAINHTML::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - int count = 0; - - SWBuf orig = text; - const char *from = orig.c_str(); - for (text = ""; *from; from++) - { - if ((*from == '\n') && (from[1] == '\n')) // two newlinea are a paragraph - { - text += "<P>"; - from++; - continue; - } else { - if ((*from == '\n')) // && (from[1] != '\n')) // only one new line - { - text += "<BR>"; - continue; - } - } - - if (*from == '{') { //footnote start - text += "<FONT COLOR=\"#80000\"><SMALL> ("; - continue; - } - else if (*from == '}') //footnote end - { - text += ") </SMALL></FONT>"; - continue; - } - else if ((*from == ' ') && (count > 5000)) - { - text += "<WBR>"; - count = 0; - continue; - } - - text += *from; - count++; - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/rtfhtml.cpp b/src/modules/filters/rtfhtml.cpp deleted file mode 100644 index 6b228fb..0000000 --- a/src/modules/filters/rtfhtml.cpp +++ /dev/null @@ -1,80 +0,0 @@ -/*************************************************************************** - rtfhtml.cpp - description - ------------------- - begin : Wed Oct 13 1999 - copyright : (C) 1999 by The team of BibleTime - email : info@bibletime.de - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include <stdlib.h> -#include <rtfhtml.h> - -SWORD_NAMESPACE_START - -RTFHTML::RTFHTML() { - -} - - -char RTFHTML::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - bool center = false; - - const char *from; - SWBuf orig = text; - from = orig.c_str(); - for (text = ""; *from; from++) - { - if (*from == '\\') // a RTF command - { - if ( !strncmp(from+1, "pard", 4) ) - //(from[1] == 'p') && (from[2] == 'a') && (from[3] == 'r') && (from[4] == 'd')) - { // switch all modifiers off - if (center) - { - text += "</CENTER>"; - center = false; - } - from += 4; - continue; - } - if ( !strncmp(from+1, "par", 3) ) - //(from[1] == 'p') && (from[2] == 'a') && (from[3] == 'r')) - { - text += "<P>\n"; - from += 3; - continue; - } - if (from[1] == ' ') - { - from += 1; - continue; - } - if ( !strncmp(from+1, "qc", 2) ) - //(from[1] == 'q') && (from[2] == 'c')) // center on - { - if (!center) - { - text += "<CENTER>"; - center = true; - } - from += 2; - continue; - } - } - - text += *from; - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/scsuutf8.cpp b/src/modules/filters/scsuutf8.cpp deleted file mode 100644 index aff265d..0000000 --- a/src/modules/filters/scsuutf8.cpp +++ /dev/null @@ -1,226 +0,0 @@ -/****************************************************************************** - * - * SCSUUTF8 - SWFilter descendant to convert a SCSU character to UTF-8 - * - */ - - -/* This class is based on: - * http://czyborra.com/scsu/scsu.c written by Roman Czyborra@dds.nl - * on Andrea's balcony in North Amsterdam on 1998-08-04 - * Thanks to Richard Verhoeven <rcb5@win.tue.nl> for his suggestion - * to correct the haphazard "if" after UQU to "else if" on 1998-10-01 - * - * This is a deflator to UTF-8 output for input compressed in SCSU, - * the (Reuters) Standard Compression Scheme for Unicode as described - * in http://www.unicode.org/unicode/reports/tr6.html - */ - -#include <stdlib.h> -#include <stdio.h> -#include <swmodule.h> - -#include <scsuutf8.h> - -SWORD_NAMESPACE_START - -SCSUUTF8::SCSUUTF8() { -} - - -unsigned char* SCSUUTF8::UTF8Output(unsigned long uchar, unsigned char* text) -{ - /* join UTF-16 surrogates without any pairing sanity checks */ - - static int d; - - if (uchar >= 0xd800 && uchar <= 0xdbff) { d = uchar & 0x3f; return text; } - if (uchar >= 0xdc00 && uchar <= 0xdfff) { uchar = uchar + 0x2400 + d * 0x400; } - - /* output one character as UTF-8 multibyte sequence */ - - if (uchar < 0x80) { - *text++ = c; - } - else if (uchar < 0x800) { - *text++ = 0xc0 | uchar >> 6; - *text++ = 0x80 | uchar & 0x3f; - } - else if (uchar < 0x10000) { - *text++ = 0xe0 | uchar >> 12; - *text++ = 0x80 | uchar >> 6 & 0x3f; - *text++ = 0x80 | uchar & 0x3f; - } - else if (uchar < 0x200000) { - *text++ = 0xf0 | uchar >> 18; - *text++ = 0x80 | uchar >> 12 & 0x3f; - *text++ = 0x80 | uchar >> 6 & 0x3f; - *text++ = 0x80 | uchar & 0x3f; - } - - return text; -} - -char SCSUUTF8::processText(SWBuf &text, const SWKey *key, const SWModule *module) { -/* - unsigned char *to, *from; - unsigned long buflen = len * FILTERPAD; - char active = 0, mode = 0; - if ((unsigned long)key < 2) // hack, we're en(1)/de(0)ciphering - return -1; - - static unsigned short start[8] = {0x0000,0x0080,0x0100,0x0300,0x2000,0x2080,0x2100,0x3000}; - static unsigned short slide[8] = {0x0080,0x00C0,0x0400,0x0600,0x0900,0x3040,0x30A0,0xFF00}; - static unsigned short win[256] = { - 0x0000, 0x0080, 0x0100, 0x0180, 0x0200, 0x0280, 0x0300, 0x0380, - 0x0400, 0x0480, 0x0500, 0x0580, 0x0600, 0x0680, 0x0700, 0x0780, - 0x0800, 0x0880, 0x0900, 0x0980, 0x0A00, 0x0A80, 0x0B00, 0x0B80, - 0x0C00, 0x0C80, 0x0D00, 0x0D80, 0x0E00, 0x0E80, 0x0F00, 0x0F80, - 0x1000, 0x1080, 0x1100, 0x1180, 0x1200, 0x1280, 0x1300, 0x1380, - 0x1400, 0x1480, 0x1500, 0x1580, 0x1600, 0x1680, 0x1700, 0x1780, - 0x1800, 0x1880, 0x1900, 0x1980, 0x1A00, 0x1A80, 0x1B00, 0x1B80, - 0x1C00, 0x1C80, 0x1D00, 0x1D80, 0x1E00, 0x1E80, 0x1F00, 0x1F80, - 0x2000, 0x2080, 0x2100, 0x2180, 0x2200, 0x2280, 0x2300, 0x2380, - 0x2400, 0x2480, 0x2500, 0x2580, 0x2600, 0x2680, 0x2700, 0x2780, - 0x2800, 0x2880, 0x2900, 0x2980, 0x2A00, 0x2A80, 0x2B00, 0x2B80, - 0x2C00, 0x2C80, 0x2D00, 0x2D80, 0x2E00, 0x2E80, 0x2F00, 0x2F80, - 0x3000, 0x3080, 0x3100, 0x3180, 0x3200, 0x3280, 0x3300, 0x3800, - 0xE000, 0xE080, 0xE100, 0xE180, 0xE200, 0xE280, 0xE300, 0xE380, - 0xE400, 0xE480, 0xE500, 0xE580, 0xE600, 0xE680, 0xE700, 0xE780, - 0xE800, 0xE880, 0xE900, 0xE980, 0xEA00, 0xEA80, 0xEB00, 0xEB80, - 0xEC00, 0xEC80, 0xED00, 0xED80, 0xEE00, 0xEE80, 0xEF00, 0xEF80, - 0xF000, 0xF080, 0xF100, 0xF180, 0xF200, 0xF280, 0xF300, 0xF380, - 0xF400, 0xF480, 0xF500, 0xF580, 0xF600, 0xF680, 0xF700, 0xF780, - 0xF800, 0xF880, 0xF900, 0xF980, 0xFA00, 0xFA80, 0xFB00, 0xFB80, - 0xFC00, 0xFC80, 0xFD00, 0xFD80, 0xFE00, 0xFE80, 0xFF00, 0xFF80, - 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, - 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, - 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, - 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, - 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, - 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, - 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, - 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, - 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, - 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, - 0x0000, 0x00C0, 0x0250, 0x0370, 0x0530, 0x3040, 0x30A0, 0xFF60 - }; - - if (!len) - return 0; - - memmove(&text[buflen - len], text, len); - from = (unsigned char*)&text[buflen - len]; - to = (unsigned char *)text; - - // ------------------------------- - - for (int i = 0; i < len;) { - - - if (i >= len) break; - c = from[i++]; - - if (c >= 0x80) - { - to = UTF8Output (c - 0x80 + slide[active], to); - } - else if (c >= 0x20 && c <= 0x7F) - { - to = UTF8Output (c, to); - } - else if (c == 0x0 || c == 0x9 || c == 0xA || c == 0xC || c == 0xD) - { - to = UTF8Output (c, to); - } - else if (c >= 0x1 && c <= 0x8) // SQn - { - if (i >= len) break; - d = from[i++]; // single quote - - to = UTF8Output (d < 0x80 ? d + start [c - 0x1] : - d - 0x80 + slide [c - 0x1], to); - } - else if (c >= 0x10 && c <= 0x17) // SCn - { - active = c - 0x10; // change window - } - else if (c >= 0x18 && c <= 0x1F) // SDn - { - active = c - 0x18; // define window - if (i >= len) break; - slide [active] = win [from[i++]]; - } - else if (c == 0xB) // SDX - { - if (i >= len) break; - c = from[i++]; - - if (i >= len) break; - d = from[i++]; - - slide [active = c>>5] = 0x10000 + (((c & 0x1F) << 8 | d) << 7); - } - else if (c == 0xE) // SQU - { - if (i >= len) break; - c = from[i++]; // SQU - - if (i >= len) break; - to = UTF8Output (c << 8 | from[i++], to); - } - else if (c == 0xF) // SCU - { - mode = 1; // change to Unicode mode - - while (mode) - { - if (i >= len) break; - c = from[i++]; - - if (c <= 0xDF || c >= 0xF3) - { - if (i >= len) break; - to = UTF8Output (c << 8 | from[i++], to); - } - else if (c == 0xF0) // UQU - { - if (i >= len) break; - c = from[i++]; - - if (i >= len) break; - to = UTF8Output (c << 8 | from[i++], to); - } - else if (c >= 0xE0 && c <= 0xE7) // UCn - { - active = c - 0xE0; mode = 0; - } - else if (c >= 0xE8 && c <= 0xEF) // UDn - { - if (i >= len) break; - slide [active=c-0xE8] = win [from[i++]]; mode = 0; - } - else if (c == 0xF1) // UDX - { - if (i >= len) break; - c = from[i++]; - - if (i >= len) break; - d = from[i++]; - - slide [active = c>>5] = - 0x10000 + (((c & 0x1F) << 8 | d) << 7); mode = 0; - } - } - } - - - } - - *to++ = 0; - *to = 0; -*/ - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/swbasicfilter.cpp b/src/modules/filters/swbasicfilter.cpp deleted file mode 100644 index 55c8843..0000000 --- a/src/modules/filters/swbasicfilter.cpp +++ /dev/null @@ -1,321 +0,0 @@ -/****************************************************************************** - * swbasicfilter.h - definition of class SWBasicFilter. An SWFilter - * impl that provides some basic methods that - * many filters will need and can use as a starting - * point. - * - * $Id: swbasicfilter.cpp,v 1.33 2003/10/24 02:43:46 scribe Exp $ - * - * Copyright 2001 CrossWire Bible Society (http://www.crosswire.org) - * CrossWire Bible Society - * P. O. Box 2528 - * Tempe, AZ 85280-2528 - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation version 2. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - */ - -#include <stdlib.h> -#include <swbasicfilter.h> -#include <stdio.h> -#include <stdarg.h> - -SWORD_NAMESPACE_START - -const char SWBasicFilter::INITIALIZE = 1; -const char SWBasicFilter::PRECHAR = 2; -const char SWBasicFilter::POSTCHAR = 4; -const char SWBasicFilter::FINALIZE = 8; - -SWBasicFilter::SWBasicFilter() { - processStages = 0; - tokenStart = 0; - tokenEnd = 0; - escStart = 0; - escEnd = 0; - - setTokenStart("<"); - setTokenEnd(">"); - setEscapeStart("&"); - setEscapeEnd(";"); - - escStringCaseSensitive = false; - tokenCaseSensitive = false; - passThruUnknownToken = false; - passThruUnknownEsc = false; -} - - -void SWBasicFilter::setPassThruUnknownToken(bool val) { - passThruUnknownToken = val; -} - - -void SWBasicFilter::setPassThruUnknownEscapeString(bool val) { - passThruUnknownEsc = val; -} - - -void SWBasicFilter::setTokenCaseSensitive(bool val) { - tokenCaseSensitive = val; -} - - -void SWBasicFilter::setEscapeStringCaseSensitive(bool val) { - escStringCaseSensitive = val; -} - - -SWBasicFilter::~SWBasicFilter() { - if (tokenStart) - delete [] tokenStart; - - if (tokenEnd) - delete [] tokenEnd; - - if (escStart) - delete [] escStart; - - if (escEnd) - delete [] escEnd; -} - - -void SWBasicFilter::addTokenSubstitute(const char *findString, const char *replaceString) { - char *buf = 0; - - if (!tokenCaseSensitive) { - stdstr(&buf, findString); - toupperstr(buf); - tokenSubMap[buf] = replaceString; - delete [] buf; - } - else tokenSubMap[findString] = replaceString; -} - - -void SWBasicFilter::replaceTokenSubstitute(const char *findString, const char *replaceString) { - if (tokenSubMap.find(findString) != tokenSubMap.end()) { - tokenSubMap.erase( tokenSubMap.find(findString) ); //erase entry - } - addTokenSubstitute(findString, replaceString); -} - - -void SWBasicFilter::addEscapeStringSubstitute(const char *findString, const char *replaceString) { - char *buf = 0; - - if (!escStringCaseSensitive) { - stdstr(&buf, findString); - toupperstr(buf); - escSubMap.insert(DualStringMap::value_type(buf, replaceString)); - delete [] buf; - } - else escSubMap.insert(DualStringMap::value_type(findString, replaceString)); -} - -void SWBasicFilter::replaceEscapeStringSubstitute(const char *findString, const char *replaceString) { - if (escSubMap.find(findString) != escSubMap.end()) { - escSubMap.erase( escSubMap.find(findString) ); //erase entry - } - addEscapeStringSubstitute(findString, replaceString); -} - - -bool SWBasicFilter::substituteToken(SWBuf &buf, const char *token) { - DualStringMap::iterator it; - - if (!tokenCaseSensitive) { - char *tmp = 0; - stdstr(&tmp, token); - toupperstr(tmp); - it = tokenSubMap.find(tmp); - delete [] tmp; - } else - it = tokenSubMap.find(token); - - if (it != tokenSubMap.end()) { - buf += it->second.c_str(); - return true; - } - return false; -} - - -bool SWBasicFilter::substituteEscapeString(SWBuf &buf, const char *escString) { - DualStringMap::iterator it; - - if (!escStringCaseSensitive) { - char *tmp = 0; - stdstr(&tmp, escString); - toupperstr(tmp); - it = escSubMap.find(tmp); - delete [] tmp; - } else - it = escSubMap.find(escString); - - if (it != escSubMap.end()) { - buf += it->second.c_str(); - return true; - } - return false; -} - - -bool SWBasicFilter::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) { - return substituteToken(buf, token); -} - - -bool SWBasicFilter::handleEscapeString(SWBuf &buf, const char *escString, BasicFilterUserData *userData) { - return substituteEscapeString(buf, escString); -} - - -void SWBasicFilter::setEscapeStart(const char *escStart) { - stdstr(&(this->escStart), escStart); - escStartLen = strlen(escStart); -} - - -void SWBasicFilter::setEscapeEnd(const char *escEnd) { - stdstr(&(this->escEnd), escEnd); - escEndLen = strlen(escEnd); -} - - -void SWBasicFilter::setTokenStart(const char *tokenStart) { - stdstr(&(this->tokenStart), tokenStart); - tokenStartLen = strlen(tokenStart); -} - - -void SWBasicFilter::setTokenEnd(const char *tokenEnd) { - stdstr(&(this->tokenEnd), tokenEnd); - tokenEndLen = strlen(tokenEnd); -} - - -char SWBasicFilter::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - char *from; - char token[4096]; - int tokpos = 0; - bool intoken = false; - bool inEsc = false; - char escStartPos = 0, escEndPos = 0; - char tokenStartPos = 0, tokenEndPos = 0; - SWBuf lastTextNode; - BasicFilterUserData *userData = createUserData(module, key); - - SWBuf orig = text; - from = orig.getRawData(); - text = ""; - - if (processStages & INITIALIZE) { - if (processStage(INITIALIZE, text, from, userData)) { // processStage handled it all - delete userData; - return 0; - } - } - - for (;*from; from++) { - - if (processStages & PRECHAR) { - if (processStage(PRECHAR, text, from, userData)) // processStage handled this char - continue; - } - - if (*from == tokenStart[tokenStartPos]) { - if (tokenStartPos == (tokenStartLen - 1)) { - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - inEsc = false; - } - else tokenStartPos++; - continue; - } - - if (*from == escStart[escStartPos]) { - if (escStartPos == (escStartLen - 1)) { - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - inEsc = true; - } - else escStartPos++; - continue; - } - - if (inEsc) { - if (*from == escEnd[escEndPos]) { - if (escEndPos == (escEndLen - 1)) { - intoken = false; - userData->lastTextNode = lastTextNode; - if ((!handleEscapeString(text, token, userData)) && (passThruUnknownEsc)) { - text += escStart; - text += token; - text += escEnd; - } - escEndPos = escStartPos = tokenEndPos = tokenStartPos = 0; - lastTextNode = ""; - continue; - } - } - } - - if (!inEsc) { - if (*from == tokenEnd[tokenEndPos]) { - if (tokenEndPos == (tokenEndLen - 1)) { - intoken = false; - userData->lastTextNode = lastTextNode; - if ((!handleToken(text, token, userData)) && (passThruUnknownToken)) { - text += tokenStart; - text += token; - text += tokenEnd; - } - escEndPos = escStartPos = tokenEndPos = tokenStartPos = 0; - lastTextNode = ""; - continue; - } - } - } - - if (intoken) { - if (tokpos < 4090) - token[tokpos++] = *from; - token[tokpos+2] = 0; - } - else { - if ((!userData->supressAdjacentWhitespace) || (*from != ' ')) { - if (!userData->suspendTextPassThru) - text += *from; - lastTextNode += *from; - } - userData->supressAdjacentWhitespace = false; - } - - if (processStages & POSTCHAR) - processStage(POSTCHAR, text, from, userData); - - } - - if (processStages & FINALIZE) - processStage(FINALIZE, text, from, userData); - - delete userData; - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/swoptfilter.cpp b/src/modules/filters/swoptfilter.cpp deleted file mode 100644 index 4eb3c82..0000000 --- a/src/modules/filters/swoptfilter.cpp +++ /dev/null @@ -1,38 +0,0 @@ -/****************************************************************************** - * - * swoptfilter - SWFilter descendant and base class for all option filters - */ - - -#include <swoptfilter.h> - -SWORD_NAMESPACE_START - - -SWOptionFilter::SWOptionFilter(const char *oName, const char *oTip, const StringList *oValues) { - optName = oName; - optTip = oTip; - optValues = oValues; -} - - -SWOptionFilter::~SWOptionFilter() { -} - - -void SWOptionFilter::setOptionValue(const char *ival) { - for (StringList::const_iterator loop = optValues->begin(); loop != optValues->end(); loop++) { - if (!stricmp(loop->c_str(), ival)) { - optionValue = *loop; - option = (!stricmp(ival, "On")); // convenience for boolean filters - break; - } - } -} - -const char *SWOptionFilter::getOptionValue() { - return optionValue; -} - - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmlfootnotes.cpp b/src/modules/filters/thmlfootnotes.cpp deleted file mode 100644 index 8b52d98..0000000 --- a/src/modules/filters/thmlfootnotes.cpp +++ /dev/null @@ -1,127 +0,0 @@ -/****************************************************************************** - * - * thmlfootnotes - SWFilter descendant to hide or show footnotes - * in a ThML module. - */ - - -#include <stdlib.h> -#include <thmlfootnotes.h> -#include <swmodule.h> -#include <swbuf.h> -#include <versekey.h> -#include <utilxml.h> -#ifndef __GNUC__ -#else -#include <unixstr.h> -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Footnotes"; -const char oTip[] = "Toggles Footnotes On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -ThMLFootnotes::ThMLFootnotes() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -ThMLFootnotes::~ThMLFootnotes() { -} - - -char ThMLFootnotes::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - SWBuf token; - bool intoken = false; - bool hide = false; - SWBuf tagText; - XMLTag startTag; - SWBuf refs = ""; - int footnoteNum = 1; - char buf[254]; - VerseKey parser = key->getText(); - - SWBuf orig = text; - const char *from = orig.c_str(); - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - token = ""; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - - XMLTag tag(token); - if (!strcmp(tag.getName(), "note")) { - if (!tag.isEndTag()) { - if (!tag.isEmpty()) { - refs = ""; - startTag = tag; - hide = true; - tagText = ""; - continue; - } - } - if (hide && tag.isEndTag()) { - if (module->isProcessEntryAttributes()) { - SWBuf fc = module->getEntryAttributes()["Footnote"]["count"]["value"]; - footnoteNum = (fc.length()) ? atoi(fc.c_str()) : 0; - sprintf(buf, "%i", ++footnoteNum); - module->getEntryAttributes()["Footnote"]["count"]["value"] = buf; - StringList attributes = startTag.getAttributeNames(); - for (StringList::iterator it = attributes.begin(); it != attributes.end(); it++) { - module->getEntryAttributes()["Footnote"][buf][it->c_str()] = startTag.getAttribute(it->c_str()); - } - module->getEntryAttributes()["Footnote"][buf]["body"] = tagText; - startTag.setAttribute("swordFootnote", buf); - if ((startTag.getAttribute("type")) && (!strcmp(startTag.getAttribute("type"), "crossReference"))) { - if (!refs.length()) - refs = parser.ParseVerseList(tagText.c_str(), parser, true).getRangeText(); - module->getEntryAttributes()["Footnote"][buf]["refList"] = refs.c_str(); - } - } - hide = false; - if ((option) || ((startTag.getAttribute("type") && (!strcmp(startTag.getAttribute("type"), "crossReference"))))) { // we want the tag in the text; crossReferences are handled by another filter - text += startTag; - text.append(tagText); - } - else continue; - } - } - - // if not a note token, keep token in text - if ((!strcmp(tag.getName(), "scripRef")) && (!tag.isEndTag())) { - SWBuf osisRef = tag.getAttribute("passage"); - if (refs.length()) - refs += "; "; - refs += osisRef; - } - if (!hide) { - text += '<'; - text.append(token); - text += '>'; - } - else { - tagText += '<'; - tagText.append(token); - tagText += '>'; - } - continue; - } - if (intoken) { //copy token - token += *from; - } - else if (!hide) { //copy text which is not inside a token - text += *from; - } - else tagText += *from; - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmlgbf.cpp b/src/modules/filters/thmlgbf.cpp deleted file mode 100644 index a65ddaf..0000000 --- a/src/modules/filters/thmlgbf.cpp +++ /dev/null @@ -1,283 +0,0 @@ -/*************************************************************************** - thmlgbf.cpp - ThML to GBF filter - ------------------- - begin : 1999-10-28 - copyright : 2001 by CrossWire Bible Society - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include <stdlib.h> -#include <thmlgbf.h> - -SWORD_NAMESPACE_START - -ThMLGBF::ThMLGBF() -{ -} - - -char ThMLGBF::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - const char *from; - char token[2048]; - int tokpos = 0; - bool intoken = false; - int len; - bool ampersand = false; - bool sechead = false; - bool title = false; - - SWBuf orig = text; - from = orig.c_str(); - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - ampersand = false; - continue; - } - else if (*from == '&') { - intoken = true; - tokpos = 0; - memset(token, 0, 2048); - ampersand = true; - continue; - } - if (*from == ';' && ampersand) { - intoken = false; - - if (!strncmp("nbsp", token, 4)) text += ' '; - else if (!strncmp("quot", token, 4)) text += '"'; - else if (!strncmp("amp", token, 3)) text += '&'; - else if (!strncmp("lt", token, 2)) text += '<'; - else if (!strncmp("gt", token, 2)) text += '>'; - else if (!strncmp("brvbar", token, 6)) text += '|'; - else if (!strncmp("sect", token, 4)) text += '§'; - else if (!strncmp("copy", token, 4)) text += '©'; - else if (!strncmp("laquo", token, 5)) text += '«'; - else if (!strncmp("reg", token, 3)) text += '®'; - else if (!strncmp("acute", token, 5)) text += '´'; - else if (!strncmp("para", token, 4)) text += '¶'; - else if (!strncmp("raquo", token, 5)) text += '»'; - - else if (!strncmp("Aacute", token, 6)) text += 'Á'; - else if (!strncmp("Agrave", token, 6)) text += 'À'; - else if (!strncmp("Acirc", token, 5)) text += 'Â'; - else if (!strncmp("Auml", token, 4)) text += 'Ä'; - else if (!strncmp("Atilde", token, 6)) text += 'Ã'; - else if (!strncmp("Aring", token, 5)) text += 'Å'; - else if (!strncmp("aacute", token, 6)) text += 'á'; - else if (!strncmp("agrave", token, 6)) text += 'à'; - else if (!strncmp("acirc", token, 5)) text += 'â'; - else if (!strncmp("auml", token, 4)) text += 'ä'; - else if (!strncmp("atilde", token, 6)) text += 'ã'; - else if (!strncmp("aring", token, 5)) text += 'å'; - else if (!strncmp("Eacute", token, 6)) text += 'É'; - else if (!strncmp("Egrave", token, 6)) text += 'È'; - else if (!strncmp("Ecirc", token, 5)) text += 'Ê'; - else if (!strncmp("Euml", token, 4)) text += 'Ë'; - else if (!strncmp("eacute", token, 6)) text += 'é'; - else if (!strncmp("egrave", token, 6)) text += 'è'; - else if (!strncmp("ecirc", token, 5)) text += 'ê'; - else if (!strncmp("euml", token, 4)) text += 'ë'; - else if (!strncmp("Iacute", token, 6)) text += 'Í'; - else if (!strncmp("Igrave", token, 6)) text += 'Ì'; - else if (!strncmp("Icirc", token, 5)) text += 'Î'; - else if (!strncmp("Iuml", token, 4)) text += 'Ï'; - else if (!strncmp("iacute", token, 6)) text += 'í'; - else if (!strncmp("igrave", token, 6)) text += 'ì'; - else if (!strncmp("icirc", token, 5)) text += 'î'; - else if (!strncmp("iuml", token, 4)) text += 'ï'; - else if (!strncmp("Oacute", token, 6)) text += 'Ó'; - else if (!strncmp("Ograve", token, 6)) text += 'Ò'; - else if (!strncmp("Ocirc", token, 5)) text += 'Ô'; - else if (!strncmp("Ouml", token, 4)) text += 'Ö'; - else if (!strncmp("Otilde", token, 6)) text += 'Õ'; - else if (!strncmp("oacute", token, 6)) text += 'ó'; - else if (!strncmp("ograve", token, 6)) text += 'ò'; - else if (!strncmp("ocirc", token, 5)) text += 'ô'; - else if (!strncmp("ouml", token, 4)) text += 'ö'; - else if (!strncmp("otilde", token, 6)) text += 'õ'; - else if (!strncmp("Uacute", token, 6)) text += 'Ú'; - else if (!strncmp("Ugrave", token, 6)) text += 'Ù'; - else if (!strncmp("Ucirc", token, 5)) text += 'Û'; - else if (!strncmp("Uuml", token, 4)) text += 'Ü'; - else if (!strncmp("uacute", token, 6)) text += 'ú'; - else if (!strncmp("ugrave", token, 6)) text += 'ù'; - else if (!strncmp("ucirc", token, 5)) text += 'û'; - else if (!strncmp("uuml", token, 4)) text += 'ü'; - else if (!strncmp("Yacute", token, 6)) text += 'Ý'; - else if (!strncmp("yacute", token, 6)) text += 'ý'; - else if (!strncmp("yuml", token, 4)) text += 'ÿ'; - - else if (!strncmp("deg", token, 3)) text += '°'; - else if (!strncmp("plusmn", token, 6)) text += '±'; - else if (!strncmp("sup2", token, 4)) text += '²'; - else if (!strncmp("sup3", token, 4)) text += '³'; - else if (!strncmp("sup1", token, 4)) text += '¹'; - else if (!strncmp("nbsp", token, 4)) text += 'º'; - else if (!strncmp("pound", token, 5)) text += '£'; - else if (!strncmp("cent", token, 4)) text += '¢'; - else if (!strncmp("frac14", token, 6)) text += '¼'; - else if (!strncmp("frac12", token, 6)) text += '½'; - else if (!strncmp("frac34", token, 6)) text += '¾'; - else if (!strncmp("iquest", token, 6)) text += '¿'; - else if (!strncmp("iexcl", token, 5)) text += '¡'; - else if (!strncmp("ETH", token, 3)) text += 'Ð'; - else if (!strncmp("eth", token, 3)) text += 'ð'; - else if (!strncmp("THORN", token, 5)) text += 'Þ'; - else if (!strncmp("thorn", token, 5)) text += 'þ'; - else if (!strncmp("AElig", token, 5)) text += 'Æ'; - else if (!strncmp("aelig", token, 5)) text += 'æ'; - else if (!strncmp("Oslash", token, 6)) text += 'Ø'; - else if (!strncmp("curren", token, 6)) text += '¤'; - else if (!strncmp("Ccedil", token, 6)) text += 'Ç'; - else if (!strncmp("ccedil", token, 6)) text += 'ç'; - else if (!strncmp("szlig", token, 5)) text += 'ß'; - else if (!strncmp("Ntilde", token, 6)) text += 'Ñ'; - else if (!strncmp("ntilde", token, 6)) text += 'ñ'; - else if (!strncmp("yen", token, 3)) text += '¥'; - else if (!strncmp("not", token, 3)) text += '¬'; - else if (!strncmp("ordf", token, 4)) text += 'ª'; - else if (!strncmp("uml", token, 3)) text += '¨'; - else if (!strncmp("shy", token, 3)) text += '­'; - else if (!strncmp("macr", token, 4)) text += '¯'; - continue; - - } - else if (*from == '>' && !ampersand) { - intoken = false; - // process desired tokens - if (!strncmp(token, "sync type=\"Strongs\" value=\"", 27)) { - text += "<W"; - for (unsigned int i = 27; token[i] != '\"'; i++) - text += token[i]; - text += '>'; - continue; - } - if (!strncmp(token, "sync type=\"morph\" value=\"", 25)) { - text += "<WT"; - for (unsigned int i = 25; token[i] != '\"'; i++) - text += token[i]; - text += '>'; - continue; - } - else if (!strncmp(token, "scripRef", 8)) { - text += "<RX>"; - continue; - } - else if (!strncmp(token, "/scripRef", 9)) { - text += "<Rx>"; - continue; - } - else if (!strncmp(token, "note", 4)) { - text += "<RF>"; - continue; - } - else if (!strncmp(token, "/note", 5)) { - text += "<Rf>"; - continue; - } - else if (!strncmp(token, "sup", 3)) { - text += "<FS>"; - } - else if (!strncmp(token, "/sup", 4)) { - text += "<Fs>"; - } - else if (!strnicmp(token, "font color=#ff0000", 18)) { - text += "<FR>"; - continue; - } - else if (!strnicmp(token, "/font", 5)) { - text += "<Fr>"; - continue; - } - else if (!strncmp(token, "div class=\"sechead\"", 19)) { - text += "<TS>"; - sechead = true; - continue; - } - else if (sechead && !strncmp(token, "/div", 19)) { - text += "<Ts>"; - sechead = false; - continue; - } - else if (!strncmp(token, "div class=\"title\"", 19)) { - text += "<TT>"; - title = true; - continue; - } - else if (title && !strncmp(token, "/div", 19)) { - text += "<Tt>"; - title = false; - continue; - } - else if (!strnicmp(token, "br", 2)) { - text += "<CL>"; - continue; - } - else switch(*token) { - case 'I': // font tags - case 'i': - text += "<FI>"; - continue; - case 'B': // bold start - case 'b': - text += "<FB>"; - continue; - case '/': - switch(token[1]) { - case 'P': - case 'p': - text += "<CM>"; - continue; - case 'I': - case 'i': // italic end - text += "<Fi>"; - continue; - case 'B': // bold start - case 'b': - text += "<Fb>"; - continue; - } - } - continue; - } - if (intoken) { - if (tokpos < 2045) - token[tokpos++] = *from; - token[tokpos+2] = 0; - } - else text += *from; - } - - orig = text; - from = orig.c_str(); - for (text = ""; *from; from++) { //loop to remove extra spaces - if ((strchr(" \t\n\r", *from))) { - while (*(from+1) && (strchr(" \t\n\r", *(from+1)))) { - from++; - } - text += " "; - } - else { - text += *from; - } - } - text += (char)0; - - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmlheadings.cpp b/src/modules/filters/thmlheadings.cpp deleted file mode 100644 index bc764bb..0000000 --- a/src/modules/filters/thmlheadings.cpp +++ /dev/null @@ -1,96 +0,0 @@ -/****************************************************************************** - * - * thmlheadings - SWFilter descendant to hide or show headings - * in a ThML module. - */ - - -#include <stdlib.h> -#include <thmlheadings.h> -#include <utilxml.h> - -#include <iostream> - -#ifndef __GNUC__ -#else -#include <unixstr.h> -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Headings"; -const char oTip[] = "Toggles Headings On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -ThMLHeadings::ThMLHeadings() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -ThMLHeadings::~ThMLHeadings() { -} - - -char ThMLHeadings::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - if (!option) { // if we don't want headings - SWBuf token; - bool intoken = false; - bool hide = false; - - SWBuf orig = text; - const char *from = orig.c_str(); - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - token = ""; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - - XMLTag tag(token); - - if (!stricmp(tag.getName(), "div")) { //we only want a div tag - //std::cout << tag.toString() << " " << tag.isEndTag() << std::endl; - - if (tag.getAttribute("class") && !stricmp(tag.getAttribute("class"), "sechead")) { - hide = true; - continue; - } - - if (tag.getAttribute("class") && !stricmp(tag.getAttribute("class"), "title")) { - hide = true; - continue; - } - - if (hide && tag.isEndTag()) { - hide = false; - continue; - } - - } - - // if not a heading token, keep token in text - if (!hide) { - text += '<'; - text += token; - text += '>'; - } - continue; - } - - if (intoken) { //copy token - token += *from; - } - else if (!hide) { //copy text which is not inside a token - text += *from; - } - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmlhtml.cpp b/src/modules/filters/thmlhtml.cpp deleted file mode 100644 index 40b3320..0000000 --- a/src/modules/filters/thmlhtml.cpp +++ /dev/null @@ -1,226 +0,0 @@ -/*************************************************************************** - thmlhtml.cpp - ThML to HTML filter - ------------------- - begin : 1999-10-27 - copyright : 2001 by CrossWire Bible Society - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include <stdlib.h> -#include <thmlhtml.h> -#include <swmodule.h> -#include <utilxml.h> - -SWORD_NAMESPACE_START - -ThMLHTML::ThMLHTML() { - setTokenStart("<"); - setTokenEnd(">"); -/* - setEscapeStart("&"); - setEscapeEnd(";"); - - setEscapeStringCaseSensitive(true); - - addEscapeStringSubstitute("nbsp", " "); - addEscapeStringSubstitute("quot", "\""); - addEscapeStringSubstitute("amp", "&"); - addEscapeStringSubstitute("lt", "<"); - addEscapeStringSubstitute("gt", ">"); - addEscapeStringSubstitute("brvbar", "|"); - addEscapeStringSubstitute("sect", "§"); - addEscapeStringSubstitute("copy", "©"); - addEscapeStringSubstitute("laquo", "«"); - addEscapeStringSubstitute("reg", "®"); - addEscapeStringSubstitute("acute", "´"); - addEscapeStringSubstitute("para", "¶"); - addEscapeStringSubstitute("raquo", "»"); - - addEscapeStringSubstitute("Aacute", "Á"); - addEscapeStringSubstitute("Agrave", "À"); - addEscapeStringSubstitute("Acirc", "Â"); - addEscapeStringSubstitute("Auml", "Ä"); - addEscapeStringSubstitute("Atilde", "Ã"); - addEscapeStringSubstitute("Aring", "Å"); - addEscapeStringSubstitute("aacute", "á"); - addEscapeStringSubstitute("agrave", "à"); - addEscapeStringSubstitute("acirc", "â"); - addEscapeStringSubstitute("auml", "ä"); - addEscapeStringSubstitute("atilde", "ã"); - addEscapeStringSubstitute("aring", "å"); - addEscapeStringSubstitute("Eacute", "É"); - addEscapeStringSubstitute("Egrave", "È"); - addEscapeStringSubstitute("Ecirc", "Ê"); - addEscapeStringSubstitute("Euml", "Ë"); - addEscapeStringSubstitute("eacute", "é"); - addEscapeStringSubstitute("egrave", "è"); - addEscapeStringSubstitute("ecirc", "ê"); - addEscapeStringSubstitute("euml", "ë"); - addEscapeStringSubstitute("Iacute", "Í"); - addEscapeStringSubstitute("Igrave", "Ì"); - addEscapeStringSubstitute("Icirc", "Î"); - addEscapeStringSubstitute("Iuml", "Ï"); - addEscapeStringSubstitute("iacute", "í"); - addEscapeStringSubstitute("igrave", "ì"); - addEscapeStringSubstitute("icirc", "î"); - addEscapeStringSubstitute("iuml", "ï"); - addEscapeStringSubstitute("Oacute", "Ó"); - addEscapeStringSubstitute("Ograve", "Ò"); - addEscapeStringSubstitute("Ocirc", "Ô"); - addEscapeStringSubstitute("Ouml", "Ö"); - addEscapeStringSubstitute("Otilde", "Õ"); - addEscapeStringSubstitute("oacute", "ó"); - addEscapeStringSubstitute("ograve", "ò"); - addEscapeStringSubstitute("ocirc", "ô"); - addEscapeStringSubstitute("ouml", "ö"); - addEscapeStringSubstitute("otilde", "õ"); - addEscapeStringSubstitute("Uacute", "Ú"); - addEscapeStringSubstitute("Ugrave", "Ù"); - addEscapeStringSubstitute("Ucirc", "Û"); - addEscapeStringSubstitute("Uuml", "Ü"); - addEscapeStringSubstitute("uacute", "ú"); - addEscapeStringSubstitute("ugrave", "ù"); - addEscapeStringSubstitute("ucirc", "û"); - addEscapeStringSubstitute("uuml", "ü"); - addEscapeStringSubstitute("Yacute", "Ý"); - addEscapeStringSubstitute("yacute", "ý"); - addEscapeStringSubstitute("yuml", "ÿ"); - - addEscapeStringSubstitute("deg", "°"); - addEscapeStringSubstitute("plusmn", "±"); - addEscapeStringSubstitute("sup2", "²"); - addEscapeStringSubstitute("sup3", "³"); - addEscapeStringSubstitute("sup1", "¹"); - addEscapeStringSubstitute("nbsp", "º"); - addEscapeStringSubstitute("pound", "£"); - addEscapeStringSubstitute("cent", "¢"); - addEscapeStringSubstitute("frac14", "¼"); - addEscapeStringSubstitute("frac12", "½"); - addEscapeStringSubstitute("frac34", "¾"); - addEscapeStringSubstitute("iquest", "¿"); - addEscapeStringSubstitute("iexcl", "¡"); - addEscapeStringSubstitute("ETH", "Ð"); - addEscapeStringSubstitute("eth", "ð"); - addEscapeStringSubstitute("THORN", "Þ"); - addEscapeStringSubstitute("thorn", "þ"); - addEscapeStringSubstitute("AElig", "Æ"); - addEscapeStringSubstitute("aelig", "æ"); - addEscapeStringSubstitute("Oslash", "Ø"); - addEscapeStringSubstitute("curren", "¤"); - addEscapeStringSubstitute("Ccedil", "Ç"); - addEscapeStringSubstitute("ccedil", "ç"); - addEscapeStringSubstitute("szlig", "ß"); - addEscapeStringSubstitute("Ntilde", "Ñ"); - addEscapeStringSubstitute("ntilde", "ñ"); - addEscapeStringSubstitute("yen", "¥"); - addEscapeStringSubstitute("not", "¬"); - addEscapeStringSubstitute("ordf", "ª"); - addEscapeStringSubstitute("uml", "¨"); - addEscapeStringSubstitute("shy", "­"); - addEscapeStringSubstitute("macr", "¯"); -*/ - setTokenCaseSensitive(true); - - addTokenSubstitute("note", " <font color=\"#800000\"><small>("); - addTokenSubstitute("/note", ")</small></font> "); -} - - -bool ThMLHTML::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) { - if (!substituteToken(buf, token)) { // manually process if it wasn't a simple substitution - MyUserData *u = (MyUserData *)userData; - XMLTag tag(token); - if (!strcmp(tag.getName(), "sync")) { - if (tag.getAttribute("type") && tag.getAttribute("value") && !strcmp(tag.getAttribute("type"), "Strongs")) { - const char* value = tag.getAttribute("value"); - if (*value == 'H' || *value == 'G' || *value == 'A') { - value++; - buf += "<small><em>"; - buf += value; - buf += "</em></small>"; - } - else if (*value == 'T') { - value += 2; - - buf += "<small><i>"; - buf += value; - buf += "</i></small>"; - } - } - else if (tag.getAttribute("type") && tag.getAttribute("value") && !strcmp(tag.getAttribute("type"), "morph")) { - buf += "<small><em>"; - buf += tag.getAttribute("value"); - buf += "</em></small>"; - } - else if (tag.getAttribute("type") && tag.getAttribute("value") && !strcmp(tag.getAttribute("type"), "lemma")) { - buf += "<small><em>("; - buf += tag.getAttribute("value"); - buf += ")</em></small>"; - } - } - else if (!strcmp(tag.getName(), "div")) { - if (tag.isEndTag() && (u->SecHead)) { - buf += "</i></b><br />"; - u->SecHead = false; - } - else if (tag.getAttribute("class")) { - if (!strcmp(tag.getAttribute("class"), "sechead")) { - u->SecHead = true; - buf += "<br /><b><i>"; - } - else if (!strcmp(tag.getAttribute("class"), "title")) { - u->SecHead = true; - buf += "<br /><b><i>"; - } - } - } - else if (!strcmp(tag.getName(), "img")) { - const char *src = strstr(token, "src"); - if (!src) // assert we have a src attribute - return false; - - buf += '<'; - for (const char *c = token; *c; c++) { - if (c == src) { - for (;((*c) && (*c != '"')); c++) - buf += *c; - - if (!*c) { c--; continue; } - - buf += '"'; - if (*(c+1) == '/') { - buf += "file:"; - buf += userData->module->getConfigEntry("AbsoluteDataPath"); - if (buf[buf.length()-2] == '/') - c++; // skip '/' - } - continue; - } - buf += *c; - } - buf += '>'; - } - else if (!strcmp(tag.getName(), "scripRef")) { //do nothing with scrip refs, we leave them out - - } - else { - buf += '<'; - buf += token; - buf += '>'; - -// return false; // we still didn't handle token - } - } - return true; -} - - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmlhtmlhref.cpp b/src/modules/filters/thmlhtmlhref.cpp deleted file mode 100644 index b94b8ae..0000000 --- a/src/modules/filters/thmlhtmlhref.cpp +++ /dev/null @@ -1,209 +0,0 @@ -/*************************************************************************** - thmlhtmlhref.cpp - ThML to HTML filter with hrefs - ------------------- - begin : 2001-09-03 - copyright : 2001 by CrossWire Bible Society - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include <stdlib.h> -#include <thmlhtmlhref.h> -#include <swmodule.h> -#include <utilxml.h> -#include <versekey.h> - -SWORD_NAMESPACE_START - - -ThMLHTMLHREF::MyUserData::MyUserData(const SWModule *module, const SWKey *key) : BasicFilterUserData(module, key) { - if (module) { - version = module->Name(); - BiblicalText = (!strcmp(module->Type(), "Biblical Texts")); - } -} - - -ThMLHTMLHREF::ThMLHTMLHREF() { - setTokenStart("<"); - setTokenEnd(">"); - - setTokenCaseSensitive(true); - addTokenSubstitute("scripture", "<i> "); - addTokenSubstitute("/scripture", "</i> "); -} - - -bool ThMLHTMLHREF::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) { - const char *tok; - if (!substituteToken(buf, token)) { // manually process if it wasn't a simple substitution - MyUserData *u = (MyUserData *)userData; - - XMLTag tag(token); - if ((!tag.isEndTag()) && (!tag.isEmpty())) - u->startTag = tag; - - if (tag.getName() && !strcmp(tag.getName(), "sync")) { - SWBuf value = tag.getAttribute("value"); - if (tag.getAttribute("type") && !strcmp(tag.getAttribute("type"), "morph")) { //> - buf += "<small><em>(<a href=\""; - buf += "type="; - buf += tag.getAttribute("type"); - - //const char* value = tag.getAttribute("value"); - buf += " value="; - buf += (value.length()) ? value.c_str() : ""; - buf += "\">"; - buf += (value.length()) ? value.c_str() : ""; - buf += "</a>) </em></small>"; - } - else if (tag.getAttribute("type") && !strcmp(tag.getAttribute("type"), "Strongs")) { - buf += "<small><em><<a href=\""; - buf += "type="; - buf += tag.getAttribute("type"); - - //const char* value = tag.getAttribute("value"); - buf += " value="; - buf += (value.length()) ? value.c_str() : ""; - buf += "\">"; - value<<1; - buf += (value.length()) ? value.c_str() : ""; - buf += "</a>> </em></small>"; - } - else if (tag.getAttribute("type") && !strcmp(tag.getAttribute("type"), "Dict")) { - if (!tag.isEndTag()) - buf += "<b>"; - else buf += "</b>"; - } - - } - // <note> tag - else if (!strcmp(tag.getName(), "note")) { - if (!tag.isEndTag()) { - if (!tag.isEmpty()) { - SWBuf type = tag.getAttribute("type"); - SWBuf footnoteNumber = tag.getAttribute("swordFootnote"); - VerseKey *vkey; - // see if we have a VerseKey * or descendant - try { - vkey = SWDYNAMIC_CAST(VerseKey, u->key); - } - catch ( ... ) { } - if (vkey) { - // leave this special osis type in for crossReference notes types? Might thml use this some day? Doesn't hurt. - char ch = ((tag.getAttribute("type") && ((!strcmp(tag.getAttribute("type"), "crossReference")) || (!strcmp(tag.getAttribute("type"), "x-cross-ref")))) ? 'x':'n'); - buf.appendFormatted("<a href=\"noteID=%s.%c.%s\"><small><sup>*%c</sup></small></a> ", vkey->getText(), ch, footnoteNumber.c_str(), ch); - } - u->suspendTextPassThru = true; - } - } - if (tag.isEndTag()) { - u->suspendTextPassThru = false; - } - } - // <scripRef> tag - else if (!strcmp(tag.getName(), "scripRef")) { - if (!tag.isEndTag()) { - if (!tag.isEmpty()) { - u->suspendTextPassThru = true; - } - } - if (tag.isEndTag()) { // </scripRef> - if (!u->BiblicalText) { - SWBuf refList = u->startTag.getAttribute("passage"); - if (!refList.length()) - refList = u->lastTextNode; - SWBuf version = tag.getAttribute("version"); - buf += " <a href=\""; - if (version.length()) { - buf += "version="; - buf += version; - buf += " "; - } - buf += "passage="; - buf += refList.c_str(); - buf += "\">"; - buf += u->lastTextNode.c_str(); - buf += "</a> "; - } - else { - SWBuf footnoteNumber = u->startTag.getAttribute("swordFootnote"); - VerseKey *vkey; - // see if we have a VerseKey * or descendant - try { - vkey = SWDYNAMIC_CAST(VerseKey, u->key); - } - catch ( ... ) {} - if (vkey) { - // leave this special osis type in for crossReference notes types? Might thml use this some day? Doesn't hurt. - buf.appendFormatted("<a href=\"noteID=%s.x.%s\"><small><sup>*x</sup></small></a> ", vkey->getText(), footnoteNumber.c_str()); - } - } - - // let's let text resume to output again - u->suspendTextPassThru = false; - } - } - else if (tag.getName() && !strcmp(tag.getName(), "div")) { - if (tag.isEndTag() && u->SecHead) { - buf += "</i></b><br />"; - u->SecHead = false; - } - else if (tag.getAttribute("class")) { - if (!stricmp(tag.getAttribute("class"), "sechead")) { - u->SecHead = true; - buf += "<br /><b><i>"; - } - else if (!stricmp(tag.getAttribute("class"), "title")) { - u->SecHead = true; - buf += "<br /><b><i>"; - } - } - } - else if (tag.getName() && (!strcmp(tag.getName(), "img") || !strcmp(tag.getName(), "image"))) { - const char *src = strstr(token, "src"); - if (!src) // assert we have a src attribute - return false; - - buf += '<'; - for (const char *c = token; *c; c++) { - if (c == src) { - for (;((*c) && (*c != '"')); c++) - buf += *c; - - if (!*c) { c--; continue; } - - buf += '"'; - if (*(c+1) == '/') { - buf += "file:"; - buf += userData->module->getConfigEntry("AbsoluteDataPath"); - if (buf[buf.length()-2] == '/') - c++; // skip '/' - } - continue; - } - buf += *c; - } - buf += '>'; - } - else { - buf += '<'; - /*for (const char *tok = token; *tok; tok++) - buf += *tok;*/ - buf += token; - buf += '>'; - //return false; // we still didn't handle token - } - } - return true; -} - - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmllemma.cpp b/src/modules/filters/thmllemma.cpp deleted file mode 100644 index 02939df..0000000 --- a/src/modules/filters/thmllemma.cpp +++ /dev/null @@ -1,69 +0,0 @@ -/****************************************************************************** - * - * thmllemma - SWFilter descendant to hide or show lemmas - * in a ThML module. - */ - - -#include <stdlib.h> -#include <thmllemma.h> -#ifndef __GNUC__ -#else -#include <unixstr.h> -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Lemmas"; -const char oTip[] = "Toggles Lemmas On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -ThMLLemma::ThMLLemma() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -ThMLLemma::~ThMLLemma() { -} - - -char ThMLLemma::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - if (!option) { // if we don't want lemmas - bool intoken = false; - - SWBuf token; - SWBuf orig = text; - const char *from = orig.c_str(); - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - token = ""; - continue; - } - else if (*from == '>') { // process tokens - intoken = false; - if (!strnicmp(token.c_str(), "sync", 4) && strstr(token.c_str(), " type=\"lemma\"")) { // Lemma - continue; - } - - // if not a lemma token, keep token in text - text += '<'; - text.append(token); - text += '>'; - continue; - } - - if (intoken) { - token += *from; - } - else { - text += *from; - } - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmlmorph.cpp b/src/modules/filters/thmlmorph.cpp deleted file mode 100644 index 606ae7e..0000000 --- a/src/modules/filters/thmlmorph.cpp +++ /dev/null @@ -1,69 +0,0 @@ -/****************************************************************************** - * - * thmlmorph - SWFilter descendant to hide or show morph tags - * in a ThML module. - */ - - -#include <stdlib.h> -#include <thmlmorph.h> -#ifndef __GNUC__ -#else -#include <unixstr.h> -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Morphological Tags"; -const char oTip[] = "Toggles Morphological Tags On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -ThMLMorph::ThMLMorph() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -ThMLMorph::~ThMLMorph() { -} - - -char ThMLMorph::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - if (!option) { // if we don't want morph tags - bool intoken = false; - - SWBuf token; - SWBuf orig = text; - const char *from = orig.c_str(); - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - token = ""; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - if (!strncmp(token.c_str(), "sync ", 5) && strstr(token.c_str(), "type=\"morph\"")) { // Morph - continue; - } - - // if not a morph tag token, keep token in text - text += '<'; - text += token; - text += '>'; - continue; - } - - if (intoken) { - token += *from; - } - else { - text += *from; - } - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmlosis.cpp b/src/modules/filters/thmlosis.cpp deleted file mode 100644 index 7208610..0000000 --- a/src/modules/filters/thmlosis.cpp +++ /dev/null @@ -1,385 +0,0 @@ -/****************************************************************************** - * - * thmlstrongs - SWFilter descendant to hide or show strongs number - * in a ThML module. - */ - - -#include <stdlib.h> -#include <stdio.h> -#include <stdarg.h> -#include <thmlosis.h> -#include <swmodule.h> -#include <swlog.h> -#include <versekey.h> -#include <stdarg.h> -#ifndef __GNUC__ -#else -#include <unixstr.h> -#endif - -SWORD_NAMESPACE_START - -ThMLOSIS::ThMLOSIS() { -} - - -ThMLOSIS::~ThMLOSIS() { -} - - -char ThMLOSIS::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - /* - - const char *from; - char token[2048]; // cheese. Fix. - int tokpos = 0; - bool intoken = false; - int len; - bool lastspace = false; - int word = 1; - char val[128]; - char buf[128]; - char wordstr[5]; - char *valto; - char *ch; - char *textStart, *textEnd; - char *wordStart, *wordEnd; - bool newText = false; - bool newWord = false; - SWBuf tmp; - bool suspendTextPassThru = false; - bool keepToken = false; - bool handled = false; - SWBuf divEnd = ""; - - - wordStart = text; - - SWBuf orig = text; - from = orig.c_str(); - - for (text = ""; *from; from++) { - - if (*from == '<') { - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - textEnd = from-1; - wordEnd = to; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - keepToken = false; - suspendTextPassThru = false; - newWord = true; - handled = false; - - while (wordStart < (text+maxlen)) { -// if (strchr(" ,;.?!()'\"", *wordStart)) - if (strchr(";,: .?!()'\"", *wordStart)) - wordStart++; - else break; - } - while (wordEnd > wordStart) { - if (strchr(" ,;:.?!()'\"", *wordEnd)) - wordEnd--; - else break; - } - - // section titles - if (!strcmp(token, "div class=\"sechead\"")) { - pushString(&to, "<title>"); - divEnd = ""; - newText = true; - lastspace = false; - handled = true; - } - else if (!strcmp(token, "/div")) { - pushString(&to, divEnd.c_str()); - lastspace = false; - handled = true; - } - // Scripture Reference - if (!strncmp(token, "scripRef", 8)) { - // pushString(buf, "Type(), "Biblical Texts")) { -// // Italics assume transchange for Biblical texts -// if (!stricmp(token, "i")) { -// pushString(&to, ""); -// newText = true; -// lastspace = false; -// handled = true; -// } -// else if (!stricmp(token, "/i")) { -// pushString(&to, ""); -// lastspace = false; -// handled = true; -// } -// } -// else { -// // otherwise, italics are just italics -//-- end italics for transchange - if (!stricmp(token, "i")) { - pushString(&to, ""); - newText = true; - lastspace = false; - handled = true; - } - else if (!stricmp(token, "/i")) { - pushString(&to, ""); - lastspace = false; - handled = true; - } -// } - - if (!strcmp(token, "b")) { - pushString(&to, ""); - newText = true; - lastspace = false; - handled = true; - } - else if (!strcmp(token, "/b")) { - pushString(&to, ""); - lastspace = false; - handled = true; - } - - // Footnote - if (!strcmp(token, "note")) { - pushString(&to, ""); - newText = true; - lastspace = false; - handled = true; - } - else if (!strcmp(token, "/note")) { - pushString(&to, ""); - lastspace = false; - handled = true; - } - - // Figure - else if (!strncmp(token, "img ", 4)) { - const char *src = strstr(token, "src"); - if (!src) // assert we have a src attribute - continue; -// return false; - - pushString(&to, "

getConfigEntry("AbsoluteDataPath")); -// if (*((*buf)-1) == '/') -// c++; // skip '/' -// } -// end of uncomment for asolute path logic - - for (c++;((*c) && (*c != '"')); c++) - *to++ = *c; - - pushString(&to, "\" />"); - handled = true; - } - - // Strongs numbers - else if (!strnicmp(token, "sync type=\"Strongs\" ", 20)) { // Strongs - if (module->isProcessEntryAttributes()) { - valto = val; - for (unsigned int i = 27; token[i] != '\"' && i < 150; i++) - *valto++ = token[i]; - *valto = 0; - if (atoi((!isdigit(*val))?val+1:val) < 5627) { - // normal strongs number - strstrip(val); - sprintf(buf, "", val); - memmove(wordStart+strlen(buf), wordStart, (to-wordStart)+1); - memcpy(wordStart, buf, strlen(buf)); - to+=strlen(buf); - pushString(&to, ""); - module->getEntryAttributes()["Word"][wordstr]["Strongs"] = val; -// tmp = ""; -// tmp.append(textStart, (int)(wordEnd - wordStart)); -// module->getEntryAttributes()["Word"][wordstr]["Text"] = tmp; - } - else { - // verb morph - sprintf(wordstr, "%03d", word-1); - module->getEntryAttributes()["Word"][wordstr]["Morph"] = val; - } - } - handled = true; - } - - // Morphology - else if (!strncmp(token, "sync type=\"morph\"", 17)) { - for (ch = token+17; *ch; ch++) { - if (!strncmp(ch, "class=\"", 7)) { - valto = val; - for (unsigned int i = 7; ch[i] != '\"' && i < 127; i++) - *valto++ = ch[i]; - *valto = 0; - sprintf(wordstr, "%03d", word-1); - strstrip(val); - module->getEntryAttributes()["Word"][wordstr]["MorphClass"] = val; - } - if (!strncmp(ch, "value=\"", 7)) { - valto = val; - for (unsigned int i = 7; ch[i] != '\"' && i < 127; i++) - *valto++ = ch[i]; - *valto = 0; - sprintf(wordstr, "%03d", word-1); - strstrip(val); - module->getEntryAttributes()["Word"][wordstr]["Morph"] = val; - } - } - if (!strncmp(wordStart, "getEntryAttributes()["Word"][wordstr]["Morph"].size() > 0) { - if (module->getEntryAttributes()["Word"][wordstr]["MorphClass"].size() > 0) - cls = module->getEntryAttributes()["Word"][wordstr]["MorphClass"].c_str(); - morph = module->getEntryAttributes()["Word"][wordstr]["Morph"].c_str(); - - sprintf(buf, "morph=\"x-%s:%s\" ", cls, morph); - memmove(wordStart+3+strlen(buf), wordStart+3, (to-wordStart)+1); - memcpy(wordStart+3, buf, strlen(buf)); - to+=strlen(buf); - } - } - handled = true; - } - - if (!keepToken) { // if we don't want strongs - if (!handled) { - SWLog::systemlog->LogError("Unprocessed Token: <%s>", token); -// exit(-1); - } - if (strchr(" ,:;.?!()'\"", from[1])) { - if (lastspace) - to--; - } - if (newText) {textStart = from+1; newText = false; } -// if (newWord) {wordStart = to; newWord = false; } - continue; - } - // if not a strongs token, keep token in text - *to++ = '<'; - for (char *tok = token; *tok; tok++) - *to++ = *tok; - *to++ = '>'; - if (newText) {textStart = to; newWord = false; } -// if (newWord) {wordStart = to; newWord = false; } - continue; - } - if (intoken) { - if ((tokpos < 2045) && ((*from != 10)&&(*from != 13))) { - token[tokpos++] = *from; - token[tokpos+2] = 0; - } - } - else { - if (newWord && (*from != ' ')) {wordStart = to; newWord = false; memset(to, 0, 10); } - if (!suspendTextPassThru) { - *to++ = *from; - lastspace = (*from == ' '); - } - } - } - - VerseKey *vkey = SWDYNAMIC_CAST(VerseKey, key); - if (vkey) { - char ref[254]; - if (vkey->Verse()) - sprintf(ref, "", vkey->getOSISRef()); - else *ref = 0; - if (*ref) { - memmove(text+strlen(ref), text, maxlen-strlen(ref)-1); - memcpy(text, ref, strlen(ref)); - to+=strlen(ref); - if (vkey->Verse()) { - VerseKey tmp; - tmp = *vkey; - tmp.AutoNormalize(0); - tmp.Headings(1); - sprintf(ref, ""); - pushString(&to, ref); - tmp = MAXVERSE; - if (*vkey == tmp) { - tmp.Verse(0); -// sprintf(ref, "\t
"); -// pushString(&to, ref); - tmp = MAXCHAPTER; - tmp = MAXVERSE; - if (*vkey == tmp) { - tmp.Chapter(0); - tmp.Verse(0); -// sprintf(ref, "\t
"); -// pushString(&to, ref); - } - } - } - -// else if (vkey->Chapter()) -// sprintf(ref, "\t
", vkey->getOSISRef()); -// else sprintf(ref, "\t
", vkey->getOSISRef()); - } - } - *to++ = 0; - *to = 0; -*/ - return 0; -} - - -const char *ThMLOSIS::convertToOSIS(const char *inRef, const SWKey *key) { - static SWBuf outRef; - - outRef = ""; - - VerseKey defLanguage; - ListKey verses = defLanguage.ParseVerseList(inRef, (*key), true); - const char *startFrag = inRef; - for (int i = 0; i < verses.Count(); i++) { - VerseKey *element = SWDYNAMIC_CAST(VerseKey, verses.GetElement(i)); - char buf[5120]; - char frag[5120]; - if (element) { - memmove(frag, startFrag, ((const char *)element->userData - startFrag) + 1); - frag[((const char *)element->userData - startFrag) + 1] = 0; - startFrag = (const char *)element->userData + 1; - sprintf(buf, "%s", element->LowerBound().getOSISRef(), element->UpperBound().getOSISRef(), frag); - } - else { - memmove(frag, startFrag, ((const char *)verses.GetElement(i)->userData - startFrag) + 1); - frag[((const char *)verses.GetElement(i)->userData - startFrag) + 1] = 0; - startFrag = (const char *)verses.GetElement(i)->userData + 1; - sprintf(buf, "%s", VerseKey(*verses.GetElement(i)).getOSISRef(), frag); - } - outRef+=buf; - } - return outRef.c_str(); -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmlplain.cpp b/src/modules/filters/thmlplain.cpp deleted file mode 100644 index a04d6c3..0000000 --- a/src/modules/filters/thmlplain.cpp +++ /dev/null @@ -1,210 +0,0 @@ -/****************************************************************************** - * - * thmlplain - SWFilter descendant to strip out all ThML tags or convert to - * ASCII rendered symbols. - */ - - -#include -#include - -SWORD_NAMESPACE_START - -ThMLPlain::ThMLPlain() { -} - -char ThMLPlain::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - char token[2048]; - int tokpos = 0; - bool intoken = false; - bool ampersand = false; - - const char *from; - SWBuf orig = text; - from = orig.c_str(); - for (text = ""; *from; from++) - { - if (*from == 10 || *from == 13) - from++; - if (*from == '<') { - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - ampersand = false; - continue; - } - else if (*from == '&') { - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - ampersand = true; - continue; - } - if (*from == ';' && ampersand) { - intoken = false; - - if (!strncmp("nbsp", token, 4)) text += ' '; - else if (!strncmp("quot", token, 4)) text += '"'; - else if (!strncmp("amp", token, 3)) text += '&'; - else if (!strncmp("lt", token, 2)) text += '<'; - else if (!strncmp("gt", token, 2)) text += '>'; - else if (!strncmp("brvbar", token, 6)) text += '|'; - else if (!strncmp("sect", token, 4)) text += '§'; - else if (!strncmp("copy", token, 4)) text += '©'; - else if (!strncmp("laquo", token, 5)) text += '«'; - else if (!strncmp("reg", token, 3)) text += '®'; - else if (!strncmp("acute", token, 5)) text += '´'; - else if (!strncmp("para", token, 4)) text += '¶'; - else if (!strncmp("raquo", token, 5)) text += '»'; - - else if (!strncmp("Aacute", token, 6)) text += 'Á'; - else if (!strncmp("Agrave", token, 6)) text += 'À'; - else if (!strncmp("Acirc", token, 5)) text += 'Â'; - else if (!strncmp("Auml", token, 4)) text += 'Ä'; - else if (!strncmp("Atilde", token, 6)) text += 'Ã'; - else if (!strncmp("Aring", token, 5)) text += 'Å'; - else if (!strncmp("aacute", token, 6)) text += 'á'; - else if (!strncmp("agrave", token, 6)) text += 'à'; - else if (!strncmp("acirc", token, 5)) text += 'â'; - else if (!strncmp("auml", token, 4)) text += 'ä'; - else if (!strncmp("atilde", token, 6)) text += 'ã'; - else if (!strncmp("aring", token, 5)) text += 'å'; - else if (!strncmp("Eacute", token, 6)) text += 'É'; - else if (!strncmp("Egrave", token, 6)) text += 'È'; - else if (!strncmp("Ecirc", token, 5)) text += 'Ê'; - else if (!strncmp("Euml", token, 4)) text += 'Ë'; - else if (!strncmp("eacute", token, 6)) text += 'é'; - else if (!strncmp("egrave", token, 6)) text += 'è'; - else if (!strncmp("ecirc", token, 5)) text += 'ê'; - else if (!strncmp("euml", token, 4)) text += 'ë'; - else if (!strncmp("Iacute", token, 6)) text += 'Í'; - else if (!strncmp("Igrave", token, 6)) text += 'Ì'; - else if (!strncmp("Icirc", token, 5)) text += 'Î'; - else if (!strncmp("Iuml", token, 4)) text += 'Ï'; - else if (!strncmp("iacute", token, 6)) text += 'í'; - else if (!strncmp("igrave", token, 6)) text += 'ì'; - else if (!strncmp("icirc", token, 5)) text += 'î'; - else if (!strncmp("iuml", token, 4)) text += 'ï'; - else if (!strncmp("Oacute", token, 6)) text += 'Ó'; - else if (!strncmp("Ograve", token, 6)) text += 'Ò'; - else if (!strncmp("Ocirc", token, 5)) text += 'Ô'; - else if (!strncmp("Ouml", token, 4)) text += 'Ö'; - else if (!strncmp("Otilde", token, 6)) text += 'Õ'; - else if (!strncmp("oacute", token, 6)) text += 'ó'; - else if (!strncmp("ograve", token, 6)) text += 'ò'; - else if (!strncmp("ocirc", token, 5)) text += 'ô'; - else if (!strncmp("ouml", token, 4)) text += 'ö'; - else if (!strncmp("otilde", token, 6)) text += 'õ'; - else if (!strncmp("Uacute", token, 6)) text += 'Ú'; - else if (!strncmp("Ugrave", token, 6)) text += 'Ù'; - else if (!strncmp("Ucirc", token, 5)) text += 'Û'; - else if (!strncmp("Uuml", token, 4)) text += 'Ü'; - else if (!strncmp("uacute", token, 6)) text += 'ú'; - else if (!strncmp("ugrave", token, 6)) text += 'ù'; - else if (!strncmp("ucirc", token, 5)) text += 'û'; - else if (!strncmp("uuml", token, 4)) text += 'ü'; - else if (!strncmp("Yacute", token, 6)) text += 'Ý'; - else if (!strncmp("yacute", token, 6)) text += 'ý'; - else if (!strncmp("yuml", token, 4)) text += 'ÿ'; - - else if (!strncmp("deg", token, 3)) text += '°'; - else if (!strncmp("plusmn", token, 6)) text += '±'; - else if (!strncmp("sup2", token, 4)) text += '²'; - else if (!strncmp("sup3", token, 4)) text += '³'; - else if (!strncmp("sup1", token, 4)) text += '¹'; - else if (!strncmp("nbsp", token, 4)) text += 'º'; - else if (!strncmp("pound", token, 5)) text += '£'; - else if (!strncmp("cent", token, 4)) text += '¢'; - else if (!strncmp("frac14", token, 6)) text += '¼'; - else if (!strncmp("frac12", token, 6)) text += '½'; - else if (!strncmp("frac34", token, 6)) text += '¾'; - else if (!strncmp("iquest", token, 6)) text += '¿'; - else if (!strncmp("iexcl", token, 5)) text += '¡'; - else if (!strncmp("ETH", token, 3)) text += 'Ð'; - else if (!strncmp("eth", token, 3)) text += 'ð'; - else if (!strncmp("THORN", token, 5)) text += 'Þ'; - else if (!strncmp("thorn", token, 5)) text += 'þ'; - else if (!strncmp("AElig", token, 5)) text += 'Æ'; - else if (!strncmp("aelig", token, 5)) text += 'æ'; - else if (!strncmp("Oslash", token, 6)) text += 'Ø'; - else if (!strncmp("curren", token, 6)) text += '¤'; - else if (!strncmp("Ccedil", token, 6)) text += 'Ç'; - else if (!strncmp("ccedil", token, 6)) text += 'ç'; - else if (!strncmp("szlig", token, 5)) text += 'ß'; - else if (!strncmp("Ntilde", token, 6)) text += 'Ñ'; - else if (!strncmp("ntilde", token, 6)) text += 'ñ'; - else if (!strncmp("yen", token, 3)) text += '¥'; - else if (!strncmp("not", token, 3)) text += '¬'; - else if (!strncmp("ordf", token, 4)) text += 'ª'; - else if (!strncmp("uml", token, 3)) text += '¨'; - else if (!strncmp("shy", token, 3)) text += '­'; - else if (!strncmp("macr", token, 4)) text += '¯'; - continue; - - } - else if (*from == '>' && !ampersand) { - intoken = false; - // process desired tokens - if (!strncmp(token, "sync type=\"Strongs\" value=\"", 27)) { - text += ' '; - text += '<'; - for (unsigned int i = 27; token[i] != '\"'; i++) - text += token[i]; - text += '>'; - continue; - } - if (!strncmp(token, "sync type=\"morph\" value=\"", 25)) { - text += ' '; - text += '('; - for (unsigned int i = 25; token[i] != '\"'; i++) - text += token[i]; - text += ')'; - continue; - } - if (!strncmp("note", token, 4)) { - text += ' '; - text += '('; - } - else if (!strncmp("br", token, 2)) - text += '\n'; - else if (!strncmp("/p", token, 2)) - text += '\n'; - else if (!strncmp("/note", token, 5)) { - text += ')'; - text += ' '; - } - continue; - } - if (intoken) { - if (tokpos < 2045) - token[tokpos++] = *from; - token[tokpos+2] = 0; - } - else text += *from; - } - - orig = text; - from = orig.c_str(); - for (text = ""; *from; from++) { //loop to remove extra spaces - if ((strchr(" \t\n\r", *from))) { - while (*(from+1) && (strchr(" \t\n\r", *(from+1)))) { - from++; - } - text += " "; - } - else { - text += *from; - } - } - text += (char)0; - - return 0; -} - - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmlrtf.cpp b/src/modules/filters/thmlrtf.cpp deleted file mode 100644 index 4487921..0000000 --- a/src/modules/filters/thmlrtf.cpp +++ /dev/null @@ -1,314 +0,0 @@ -/*************************************************************************** - thmlrtf.cpp - ThML to RTF filter - ------------------- - begin : 1999-10-27 - copyright : 2001 by CrossWire Bible Society - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include -#include -#include -#include -#include - -SWORD_NAMESPACE_START - -ThMLRTF::ThMLRTF() { - setTokenStart("<"); - setTokenEnd(">"); - - setEscapeStart("&"); - setEscapeEnd(";"); - - setEscapeStringCaseSensitive(true); - - addEscapeStringSubstitute("nbsp", " "); - addEscapeStringSubstitute("apos", "'"); - addEscapeStringSubstitute("quot", "\""); - addEscapeStringSubstitute("amp", "&"); - addEscapeStringSubstitute("lt", "<"); - addEscapeStringSubstitute("gt", ">"); - addEscapeStringSubstitute("brvbar", "|"); - addEscapeStringSubstitute("sect", "§"); - addEscapeStringSubstitute("copy", "©"); - addEscapeStringSubstitute("laquo", "«"); - addEscapeStringSubstitute("reg", "®"); - addEscapeStringSubstitute("acute", "´"); - addEscapeStringSubstitute("para", "¶"); - addEscapeStringSubstitute("raquo", "»"); - - addEscapeStringSubstitute("Aacute", "Á"); - addEscapeStringSubstitute("Agrave", "À"); - addEscapeStringSubstitute("Acirc", "Â"); - addEscapeStringSubstitute("Auml", "Ä"); - addEscapeStringSubstitute("Atilde", "Ã"); - addEscapeStringSubstitute("Aring", "Å"); - addEscapeStringSubstitute("aacute", "á"); - addEscapeStringSubstitute("agrave", "à"); - addEscapeStringSubstitute("acirc", "â"); - addEscapeStringSubstitute("auml", "ä"); - addEscapeStringSubstitute("atilde", "ã"); - addEscapeStringSubstitute("aring", "å"); - addEscapeStringSubstitute("Eacute", "É"); - addEscapeStringSubstitute("Egrave", "È"); - addEscapeStringSubstitute("Ecirc", "Ê"); - addEscapeStringSubstitute("Euml", "Ë"); - addEscapeStringSubstitute("eacute", "é"); - addEscapeStringSubstitute("egrave", "è"); - addEscapeStringSubstitute("ecirc", "ê"); - addEscapeStringSubstitute("euml", "ë"); - addEscapeStringSubstitute("Iacute", "Í"); - addEscapeStringSubstitute("Igrave", "Ì"); - addEscapeStringSubstitute("Icirc", "Î"); - addEscapeStringSubstitute("Iuml", "Ï"); - addEscapeStringSubstitute("iacute", "í"); - addEscapeStringSubstitute("igrave", "ì"); - addEscapeStringSubstitute("icirc", "î"); - addEscapeStringSubstitute("iuml", "ï"); - addEscapeStringSubstitute("Oacute", "Ó"); - addEscapeStringSubstitute("Ograve", "Ò"); - addEscapeStringSubstitute("Ocirc", "Ô"); - addEscapeStringSubstitute("Ouml", "Ö"); - addEscapeStringSubstitute("Otilde", "Õ"); - addEscapeStringSubstitute("oacute", "ó"); - addEscapeStringSubstitute("ograve", "ò"); - addEscapeStringSubstitute("ocirc", "ô"); - addEscapeStringSubstitute("ouml", "ö"); - addEscapeStringSubstitute("otilde", "õ"); - addEscapeStringSubstitute("Uacute", "Ú"); - addEscapeStringSubstitute("Ugrave", "Ù"); - addEscapeStringSubstitute("Ucirc", "Û"); - addEscapeStringSubstitute("Uuml", "Ü"); - addEscapeStringSubstitute("uacute", "ú"); - addEscapeStringSubstitute("ugrave", "ù"); - addEscapeStringSubstitute("ucirc", "û"); - addEscapeStringSubstitute("uuml", "ü"); - addEscapeStringSubstitute("Yacute", "Ý"); - addEscapeStringSubstitute("yacute", "ý"); - addEscapeStringSubstitute("yuml", "ÿ"); - - addEscapeStringSubstitute("deg", "°"); - addEscapeStringSubstitute("plusmn", "±"); - addEscapeStringSubstitute("sup2", "²"); - addEscapeStringSubstitute("sup3", "³"); - addEscapeStringSubstitute("sup1", "¹"); - addEscapeStringSubstitute("nbsp", "º"); - addEscapeStringSubstitute("pound", "£"); - addEscapeStringSubstitute("cent", "¢"); - addEscapeStringSubstitute("frac14", "¼"); - addEscapeStringSubstitute("frac12", "½"); - addEscapeStringSubstitute("frac34", "¾"); - addEscapeStringSubstitute("iquest", "¿"); - addEscapeStringSubstitute("iexcl", "¡"); - addEscapeStringSubstitute("ETH", "Ð"); - addEscapeStringSubstitute("eth", "ð"); - addEscapeStringSubstitute("THORN", "Þ"); - addEscapeStringSubstitute("thorn", "þ"); - addEscapeStringSubstitute("AElig", "Æ"); - addEscapeStringSubstitute("aelig", "æ"); - addEscapeStringSubstitute("Oslash", "Ø"); - addEscapeStringSubstitute("curren", "¤"); - addEscapeStringSubstitute("Ccedil", "Ç"); - addEscapeStringSubstitute("ccedil", "ç"); - addEscapeStringSubstitute("szlig", "ß"); - addEscapeStringSubstitute("Ntilde", "Ñ"); - addEscapeStringSubstitute("ntilde", "ñ"); - addEscapeStringSubstitute("yen", "¥"); - addEscapeStringSubstitute("not", "¬"); - addEscapeStringSubstitute("ordf", "ª"); - addEscapeStringSubstitute("uml", "¨"); - addEscapeStringSubstitute("shy", "­"); - addEscapeStringSubstitute("macr", "¯"); - - setTokenCaseSensitive(true); - - - addTokenSubstitute("br", "\\line "); - addTokenSubstitute("br /", "\\line "); - addTokenSubstitute("i", "{\\i1 "); - addTokenSubstitute("/i", "}"); - addTokenSubstitute("b", "{\\b1 "); - addTokenSubstitute("/b", "}"); - addTokenSubstitute("p", "\\par "); - - //we need uppercase forms for the moment to support a few early ThML modules that aren't XHTML compliant - addTokenSubstitute("BR", "\\line "); - addTokenSubstitute("I", "{\\i1 "); - addTokenSubstitute("/I", "}"); - addTokenSubstitute("B", "{\\b1 "); - addTokenSubstitute("/B", "}"); - addTokenSubstitute("P", "\\par "); - addTokenSubstitute("scripture", "{\\i1 "); - addTokenSubstitute("/scripture", "}"); -} - - -char ThMLRTF::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - SWBasicFilter::processText(text, key, module); //handle tokens as usual - const char *from; - SWBuf orig = text; - from = orig.c_str(); - for (text = ""; *from; from++) { //loop to remove extra spaces - if ((strchr(" \t\n\r", *from))) { - while (*(from+1) && (strchr(" \t\n\r", *(from+1)))) { - from++; - } - text += " "; - } - else { - text += *from; - } - } - text += (char)0; - return 0; -} - - -ThMLRTF::MyUserData::MyUserData(const SWModule *module, const SWKey *key) : BasicFilterUserData(module, key) { - if (module) { - version = module->Name(); - BiblicalText = (!strcmp(module->Type(), "Biblical Texts")); - } -} - - -bool ThMLRTF::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) { - const char *tok; - if (!substituteToken(buf, token)) { // manually process if it wasn't a simple substitution - MyUserData *u = (MyUserData *)userData; - XMLTag tag(token); - if ((!tag.isEndTag()) && (!tag.isEmpty())) - u->startTag = tag; - if (tag.getName() && !strcmp(tag.getName(), "sync")) { - SWBuf value = tag.getAttribute("value"); - if (tag.getAttribute("type") && !strcmp(tag.getAttribute("type"), "morph")) { //> - buf.appendFormatted(" {\\cf4 \\sub (%s)}", value.c_str()); - } - else if( tag.getAttribute("type") && !strcmp(tag.getAttribute("type"), "Strongs")) { - if (value[0] == 'H' || value[0] == 'G' || value[0] == 'A') { - value<<1; - buf.appendFormatted(" {\\cf3 \\sub <%s>}", value.c_str()); - } - else if (value[0] == 'T') { - value<<1; - buf.appendFormatted(" {\\cf4 \\sub (%s)}", value.c_str()); - } - } - else if (tag.getAttribute("type") && !strcmp(tag.getAttribute("type"), "Dict")) { - if (!tag.isEndTag()) - buf += "{\\b "; - else buf += "}"; - } - } - // tag - else if (!strcmp(tag.getName(), "note")) { - if (!tag.isEndTag()) { - if (!tag.isEmpty()) { - SWBuf type = tag.getAttribute("type"); - SWBuf footnoteNumber = tag.getAttribute("swordFootnote"); - VerseKey *vkey; - // see if we have a VerseKey * or descendant - try { - vkey = SWDYNAMIC_CAST(VerseKey, u->key); - } - catch ( ... ) { } - if (vkey) { - // leave this special osis type in for crossReference notes types? Might thml use this some day? Doesn't hurt. - char ch = ((tag.getAttribute("type") && ((!strcmp(tag.getAttribute("type"), "crossReference")) || (!strcmp(tag.getAttribute("type"), "x-cross-ref")))) ? 'x':'n'); - buf.appendFormatted("{\\super *%c%i.%s} ", ch, vkey->Verse(), footnoteNumber.c_str()); - } - u->suspendTextPassThru = true; - } - } - if (tag.isEndTag()) { - u->suspendTextPassThru = false; - } - } - - - else if (!strcmp(tag.getName(), "scripRef")) { - if (!tag.isEndTag()) { - if (!tag.isEmpty()) { - u->suspendTextPassThru = true; - } - } - if (tag.isEndTag()) { // - if (!u->BiblicalText) { - SWBuf refList = u->startTag.getAttribute("passage"); - if (!refList.length()) - refList = u->lastTextNode; - SWBuf version = tag.getAttribute("version"); - buf += ""; - buf += refList.c_str(); -// buf += u->lastTextNode.c_str(); - buf += ""; - } - else { - SWBuf footnoteNumber = u->startTag.getAttribute("swordFootnote"); - VerseKey *vkey; - // see if we have a VerseKey * or descendant - try { - vkey = SWDYNAMIC_CAST(VerseKey, u->key); - } - catch ( ... ) {} - if (vkey) { - // leave this special osis type in for crossReference notes types? Might thml use this some day? Doesn't hurt. - buf.appendFormatted("{\\super *x%i.%s} ", vkey->Verse(), footnoteNumber.c_str()); - } - } - - // let's let text resume to output again - u->suspendTextPassThru = false; - } - } - - else if (tag.getName() && !strcmp(tag.getName(), "div")) { - if (tag.isEndTag() && u->SecHead) { - buf += "\\par}"; - u->SecHead = false; - } - else if (tag.getAttribute("class")) { - if (!stricmp(tag.getAttribute("class"), "sechead")) { - u->SecHead = true; - buf += "{\\par\\i1\\b1 "; - } - else if (!stricmp(tag.getAttribute("class"), "title")) { - u->SecHead = true; - buf += "{\\par\\i1\\b1 "; - } - } - } - else if (tag.getName() && (!strcmp(tag.getName(), "img") || !strcmp(tag.getName(), "image"))) { - const char *src = tag.getAttribute("src"); - if (!src) // assert we have a src attribute - return false; - - char* filepath = new char[strlen(u->module->getConfigEntry("AbsoluteDataPath")) + strlen(token)]; - *filepath = 0; - strcpy(filepath, userData->module->getConfigEntry("AbsoluteDataPath")); - strcat(filepath, src); - -// we do this because BibleCS looks for this EXACT format for an image tag - buf+=""; - delete [] filepath; - } - else { - return false; // we still didn't handle token - } - } - return true; -} - - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmlscripref.cpp b/src/modules/filters/thmlscripref.cpp deleted file mode 100644 index 7b93f90..0000000 --- a/src/modules/filters/thmlscripref.cpp +++ /dev/null @@ -1,126 +0,0 @@ -/****************************************************************************** - * - * thmlscripref - SWFilter descendant to hide or show scripture - * referebces in a ThML module. - */ - - -#include -#include -#include -#include -#include -#ifndef __GNUC__ -#else -#include -#endif - -SWORD_NAMESPACE_START - -const char oName[] = "Cross-references"; -const char oTip[] = "Toggles Scripture Cross-references On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -ThMLScripref::ThMLScripref() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("On"); -} - - -ThMLScripref::~ThMLScripref() { -} - - -char ThMLScripref::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - SWBuf token; - bool intoken = false; - bool hide = false; - SWBuf tagText; - XMLTag startTag; - SWBuf refs = ""; - int footnoteNum = 1; - char buf[254]; - VerseKey parser = key->getText(); - - SWBuf orig = text; - const char *from = orig.c_str(); - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - token = ""; - continue; - } - if (*from == '>') { // process tokens - intoken = false; - - XMLTag tag(token); - if (!strcmp(tag.getName(), "scripRef")) { - if (!tag.isEndTag()) { - if (!tag.isEmpty()) { - refs = ""; - startTag = tag; - hide = true; - tagText = ""; - continue; - } - } - if (hide && tag.isEndTag()) { - if (module->isProcessEntryAttributes()) { - SWBuf fc = module->getEntryAttributes()["Footnote"]["count"]["value"]; - footnoteNum = (fc.length()) ? atoi(fc.c_str()) : 0; - sprintf(buf, "%i", ++footnoteNum); - module->getEntryAttributes()["Footnote"]["count"]["value"] = buf; - StringList attributes = startTag.getAttributeNames(); - for (StringList::iterator it = attributes.begin(); it != attributes.end(); it++) { - module->getEntryAttributes()["Footnote"][buf][it->c_str()] = startTag.getAttribute(it->c_str()); - } - module->getEntryAttributes()["Footnote"][buf]["body"] = tagText; - startTag.setAttribute("swordFootnote", buf); - SWBuf passage = startTag.getAttribute("passage"); - if (passage.length()) - refs = parser.ParseVerseList(passage.c_str(), parser, true).getRangeText(); - else refs = parser.ParseVerseList(tagText.c_str(), parser, true).getRangeText(); - module->getEntryAttributes()["Footnote"][buf]["refList"] = refs.c_str(); - } - hide = false; - if (option) { // we want the tag in the text - text += startTag; - text.append(tagText); - } - else continue; - } - } - - // if not a scripRef token, keep token in text - if ((!strcmp(tag.getName(), "scripRef")) && (!tag.isEndTag())) { - SWBuf osisRef = tag.getAttribute("passage"); - if (refs.length()) - refs += "; "; - refs += osisRef; - } - if (!hide) { - text += '<'; - text.append(token); - text += '>'; - } - else { - tagText += '<'; - tagText.append(token); - tagText += '>'; - } - continue; - } - if (intoken) { //copy token - token += *from; - } - else if (!hide) { //copy text which is not inside a token - text += *from; - } - else tagText += *from; - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmlstrongs.cpp b/src/modules/filters/thmlstrongs.cpp deleted file mode 100644 index 4a53e25..0000000 --- a/src/modules/filters/thmlstrongs.cpp +++ /dev/null @@ -1,139 +0,0 @@ -/****************************************************************************** - * - * thmlstrongs - SWFilter descendant to hide or show strongs number - * in a ThML module. - */ - - -#include -#include -#include -#include -#ifndef __GNUC__ -#else -#include -#endif -#include - -SWORD_NAMESPACE_START - -const char oName[] = "Strong's Numbers"; -const char oTip[] = "Toggles Strong's Numbers On and Off if they exist"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -ThMLStrongs::ThMLStrongs() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -ThMLStrongs::~ThMLStrongs() { -} - - -char ThMLStrongs::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - char token[2048]; // cheese. Fix. - const char *from; - int tokpos = 0; - bool intoken = false; - int len; - bool lastspace = false; - int word = 1; - char val[128]; - char wordstr[5]; - char *valto; - char *ch; - unsigned int textStart = 0, textEnd = 0; - SWBuf tmp; - bool newText = false; - - SWBuf orig = text; - from = orig.c_str(); - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - tokpos = 0; - token[0] = 0; - token[1] = 0; - token[2] = 0; - textEnd = text.length(); - continue; - } - if (*from == '>') { // process tokens - intoken = false; - if (!strnicmp(token, "sync type=\"Strongs\" ", 20)) { // Strongs - if (module->isProcessEntryAttributes()) { - valto = val; - for (unsigned int i = 27; token[i] != '\"' && i < 150; i++) - *valto++ = token[i]; - *valto = 0; - if (atoi((!isdigit(*val))?val+1:val) < 5627) { - // normal strongs number - sprintf(wordstr, "%03d", word++); - module->getEntryAttributes()["Word"][wordstr]["Strongs"] = val; - tmp = ""; - tmp.append(text.c_str()+textStart, (int)(textEnd - textStart)); - module->getEntryAttributes()["Word"][wordstr]["Text"] = tmp; - newText = true; - } - else { - // verb morph - sprintf(wordstr, "%03d", word-1); - module->getEntryAttributes()["Word"][wordstr]["Morph"] = val; - } - } - - if (!option) { // if we don't want strongs - if ((from[1] == ' ') || (from[1] == ',') || (from[1] == ';') || (from[1] == '.') || (from[1] == '?') || (from[1] == '!') || (from[1] == ')') || (from[1] == '\'') || (from[1] == '\"')) { - if (lastspace) - text--; - } - if (newText) {textStart = text.length(); newText = false; } - continue; - } - } - if (module->isProcessEntryAttributes()) { - if (!strncmp(token, "sync type=\"morph\"", 17)) { - for (ch = token+17; *ch; ch++) { - if (!strncmp(ch, "class=\"", 7)) { - valto = val; - for (unsigned int i = 7; ch[i] != '\"' && i < 127; i++) - *valto++ = ch[i]; - *valto = 0; - sprintf(wordstr, "%03d", word-1); - module->getEntryAttributes()["Word"][wordstr]["MorphClass"] = val; - } - if (!strncmp(ch, "value=\"", 7)) { - valto = val; - for (unsigned int i = 7; ch[i] != '\"' && i < 127; i++) - *valto++ = ch[i]; - *valto = 0; - sprintf(wordstr, "%03d", word-1); - module->getEntryAttributes()["Word"][wordstr]["Morph"] = val; - } - } - } - } - // if not a strongs token, keep token in text - text += '<'; - text += token; - text += '>'; - if (newText) {textStart = text.length(); newText = false; } - continue; - } - if (intoken) { - if (tokpos < 2045) - token[tokpos++] = *from; - token[tokpos+2] = 0; - } - else { - text += *from; - lastspace = (*from == ' '); - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmlvariants.cpp b/src/modules/filters/thmlvariants.cpp deleted file mode 100644 index b8ab653..0000000 --- a/src/modules/filters/thmlvariants.cpp +++ /dev/null @@ -1,112 +0,0 @@ -/****************************************************************************** - * - * thmlvariants - SWFilter descendant to hide or show textual variants - * in a ThML module. - */ - - -#include -#include -#ifndef __GNUC__ -#else -#include -#endif - -SWORD_NAMESPACE_START - -const char ThMLVariants::primary[] = "Primary Reading"; -const char ThMLVariants::secondary[] = "Secondary Reading"; -const char ThMLVariants::all[] = "All Readings"; - -const char ThMLVariants::optName[] = "Textual Variants"; -const char ThMLVariants::optTip[] = "Switch between Textual Variants modes"; - - -ThMLVariants::ThMLVariants() { - option = false; - options.push_back(primary); - options.push_back(secondary); - options.push_back(all); -} - - -ThMLVariants::~ThMLVariants() { -} - -void ThMLVariants::setOptionValue(const char *ival) -{ - if (!stricmp(ival, primary)) option = 0; - else if (!stricmp(ival, secondary)) option = 1; - else option = 2; -} - -const char *ThMLVariants::getOptionValue() -{ - if (option == 0) { - return primary; - } - else if (option == 1) { - return secondary; - } - else { - return all; - } -} - -char ThMLVariants::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - if ( option == 0 || option == 1) { //we want primary or variant only - bool intoken = false; - bool hide = false; - - SWBuf token; - SWBuf orig = text; - const char *from = orig.c_str(); - - //we use a fixed comparision string to make sure the loop is as fast as the original two blocks with almost the same code - const char* variantCompareString = (option == 0) ? "div type=\"variant\" class=\"1\"" : "div type=\"variant\" class=\"2\""; - - for (text = ""; *from; from++) { - if (*from == '<') { - intoken = true; - token = ""; - continue; - } - else if (*from == '>') { // process tokens - intoken = false; - - if ( !strncmp(token.c_str(), variantCompareString, 28)) { //only one of the variants, length of the two strings is 28 in both cases - hide = true; - continue; - } - if (!hide) { - text += '<'; - text.append(token); - text += '>'; - } - if (!strncmp(token.c_str(), "/div", 4)) { - hide = false; - continue; - } - - continue; - } - if (intoken) { - token += *from; - } - else if (!hide) { - text += *from; - } - } - - } - - return 0; -} - - - - - - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/thmlwebif.cpp b/src/modules/filters/thmlwebif.cpp deleted file mode 100644 index f082e1e..0000000 --- a/src/modules/filters/thmlwebif.cpp +++ /dev/null @@ -1,104 +0,0 @@ -/*************************************************************************** - ThMLWEBIF.cpp - ThML to HTML filter with hrefs - ------------------- - begin : 2001-09-03 - copyright : 2001 by CrossWire Bible Society - ***************************************************************************/ - -/*************************************************************************** - * * - * This program is free software; you can redistribute it and/or modify * - * it under the terms of the GNU General Public License as published by * - * the Free Software Foundation; either version 2 of the License, or * - * (at your option) any later version. * - * * - ***************************************************************************/ - -#include -#include -#include -#include -#include -#include - -SWORD_NAMESPACE_START - -ThMLWEBIF::ThMLWEBIF() : baseURL(""), passageStudyURL(baseURL + "passagestudy.jsp") { - //all's done in ThMLHTMLHREF -} - -bool ThMLWEBIF::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) { - const char *tok; - - if (!substituteToken(buf, token)) { // manually process if it wasn't a simple substitution - MyUserData *u = (MyUserData *)userData; - XMLTag tag(token); - SWBuf url; - if (!strcmp(tag.getName(), "sync")) { - const char* value = tag.getAttribute("value"); - url = value; - if ((url.length() > 1) && strchr("GH", url[0])) { - if (isdigit(url[1])) - url = url.c_str()+1; - } - - if(tag.getAttribute("type") && !strcmp(tag.getAttribute("type"), "morph")){ - buf += " ("; - buf.appendFormatted("", passageStudyURL.c_str(), encodeURL(url).c_str() ); - } - else { - if (value) { - value++; //skip leading G, H or T - //url = value; - } - - buf += " <"; - buf.appendFormatted("", passageStudyURL.c_str(), encodeURL(url).c_str() ); - } - - buf += value; - buf += ""; - - if (tag.getAttribute("type") && !strcmp(tag.getAttribute("type"), "morph")) { - buf += ") "; - } - else { - buf += "> "; - } - } - else if (!strcmp(tag.getName(), "scripRef")) { - if (tag.isEndTag()) { - if (u->inscriptRef) { // like "John 3:16" - u->inscriptRef = false; - buf += ""; - } - else { // end of scripRef like "John 3:16" - url = u->lastTextNode; - buf.appendFormatted("", passageStudyURL.c_str(), encodeURL(url).c_str()); - buf += u->lastTextNode.c_str(); - buf += ""; - - // let's let text resume to output again - u->suspendTextPassThru = false; - } - } - else if (tag.getAttribute("passage")) { //passage given - u->inscriptRef = true; - - buf.appendFormatted("", passageStudyURL.c_str(), encodeURL(tag.getAttribute("passage")).c_str()); - } - else { //no passage given - u->inscriptRef = false; - // let's stop text from going to output - u->suspendTextPassThru = true; - } - } - else { - return ThMLHTMLHREF::handleToken(buf,token,userData); - } - } - return true; -} - - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/unicodertf.cpp b/src/modules/filters/unicodertf.cpp deleted file mode 100644 index 0a2bca8..0000000 --- a/src/modules/filters/unicodertf.cpp +++ /dev/null @@ -1,86 +0,0 @@ -/****************************************************************************** - * - * unicodertf - SWFilter descendant to convert a double byte unicode file - * to RTF tags - */ - - -#include -#include -#include - -SWORD_NAMESPACE_START - -UnicodeRTF::UnicodeRTF() { -} - - -char UnicodeRTF::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - const unsigned char *from; - char digit[10]; - unsigned long ch; - signed short utf16; - unsigned char from2[7]; - - SWBuf orig = text; - - from = (const unsigned char *)orig.c_str(); - - // ------------------------------- - for (text = ""; *from; from++) { - ch = 0; - //case: ANSI - if ((*from & 128) != 128) { - text += *from; - continue; - } - //case: Invalid UTF-8 (illegal continuing byte in initial position) - if ((*from & 128) && ((*from & 64) != 64)) { - continue; - } - //case: 2+ byte codepoint - from2[0] = *from; - from2[0] <<= 1; - int subsequent; - for (subsequent = 1; (from2[0] & 128) && (subsequent < 7); subsequent++) { - from2[0] <<= 1; - from2[subsequent] = from[subsequent]; - from2[subsequent] &= 63; - ch <<= 6; - ch |= from2[subsequent]; - } - subsequent--; - from2[0] <<= 1; - char significantFirstBits = 8 - (2+subsequent); - - ch |= (((short)from2[0]) << (((6*subsequent)+significantFirstBits)-8)); - from += subsequent; - if (ch < 0x10000) { - utf16 = (signed short)ch; - text += '\\'; - text += 'u'; - sprintf(digit, "%d", utf16); - text += digit; - text += '?'; - } - else { - utf16 = (signed short)((ch - 0x10000) / 0x400 + 0xD800); - text += '\\'; - text += 'u'; - sprintf(digit, "%d", utf16); - text += digit; - text += '?'; - utf16 = (signed short)((ch - 0x10000) % 0x400 + 0xDC00); - text += '\\'; - text += 'u'; - sprintf(digit, "%d", utf16); - text += digit; - text += '?'; - } - } - - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/utf16utf8.cpp b/src/modules/filters/utf16utf8.cpp deleted file mode 100644 index ef1593b..0000000 --- a/src/modules/filters/utf16utf8.cpp +++ /dev/null @@ -1,92 +0,0 @@ -/****************************************************************************** - * - * UTF16UTF8 - SWFilter descendant to convert UTF-16 to UTF-8 - * - */ - -#include -#include - -#include - -SWORD_NAMESPACE_START - -UTF16UTF8::UTF16UTF8() { -} - - -char UTF16UTF8::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - unsigned short *from; - - int len; - unsigned long uchar; - unsigned short schar; - if ((unsigned long)key < 2) // hack, we're en(1)/de(0)ciphering - return -1; - - len = 0; - from = (unsigned short*) text.c_str(); - while (*from) { - len += 2; - from++; - } - - SWBuf orig = text; - from = (unsigned short*)orig.c_str(); - - - // ------------------------------- - - for (text = ""; *from; from++) { - uchar = 0; - - if (*from < 0xD800 || *from > 0xDFFF) { - uchar = *from; - } - else if (*from >= 0xD800 && *from <= 0xDBFF) { - uchar = *from; - schar = *(from+1); - if (uchar < 0xDC00 || uchar > 0xDFFF) { - //error, do nothing - continue; - } - uchar &= 0x03ff; - schar &= 0x03ff; - uchar <<= 10; - uchar |= schar; - uchar += 0x10000; - from++; - } - else { - //error, do nothing - continue; - } - - if (uchar < 0x80) { - text += uchar; - } - else if (uchar < 0x800) { - text += 0xc0 | (uchar >> 6); - text += 0x80 | (uchar & 0x3f); - } - else if (uchar < 0x10000) { - text += 0xe0 | (uchar >> 12); - text += 0x80 | (uchar >> 6) & 0x3f; - text += 0x80 | uchar & 0x3f; - } - else if (uchar < 0x200000) { - text += 0xF0 | (uchar >> 18); - text += 0x80 | (uchar >> 12) & 0x3F; - text += 0x80 | (uchar >> 6) & 0x3F; - text += 0x80 | uchar & 0x3F; - } - } - - return 0; -} - - - - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/utf8arshaping.cpp b/src/modules/filters/utf8arshaping.cpp deleted file mode 100644 index 3246adc..0000000 --- a/src/modules/filters/utf8arshaping.cpp +++ /dev/null @@ -1,52 +0,0 @@ -/****************************************************************************** -* -* utf8arshaping - SWFilter descendant to perform Arabic shaping on -* UTF-8 text -*/ - -#ifdef _ICU_ - -#include - -#ifdef __GNUC__ -#include -#endif - -#include - -SWORD_NAMESPACE_START - -UTF8arShaping::UTF8arShaping() { - conv = ucnv_open("UTF-8", &err); -} - -UTF8arShaping::~UTF8arShaping() { - ucnv_close(conv); -} - -char UTF8arShaping::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - UChar *ustr, *ustr2; - if ((unsigned long)key < 2) // hack, we're en(1)/de(0)ciphering - return -1; - - int32_t len = text.length(); - ustr = new UChar[len]; - ustr2 = new UChar[len]; - - // Convert UTF-8 string to UTF-16 (UChars) - len = ucnv_toUChars(conv, ustr, len, text.c_str(), -1, &err); - - len = u_shapeArabic(ustr, len, ustr2, len, U_SHAPE_LETTERS_SHAPE | U_SHAPE_DIGITS_EN2AN, &err); - - text.setSize(text.size()*2); - len = ucnv_fromUChars(conv, text.getRawData(), text.size(), ustr2, len, &err); - text.setSize(len); - - delete [] ustr2; - delete [] ustr; - return 0; -} - -SWORD_NAMESPACE_END -#endif diff --git a/src/modules/filters/utf8bidireorder.cpp b/src/modules/filters/utf8bidireorder.cpp deleted file mode 100644 index 902047a..0000000 --- a/src/modules/filters/utf8bidireorder.cpp +++ /dev/null @@ -1,61 +0,0 @@ -/****************************************************************************** -* -* utf8cnormalizer - SWFilter descendant to perform reordering of UTF-8 -* text to visual order according to Unicode BiDi -*/ - -#ifdef _ICU_ - -#include - -#ifdef __GNUC__ -#include -#endif - -#include - -SWORD_NAMESPACE_START - -UTF8BiDiReorder::UTF8BiDiReorder() { - - conv = ucnv_open("UTF-8", &err); - -} - -UTF8BiDiReorder::~UTF8BiDiReorder() { - ucnv_close(conv); -} - -char UTF8BiDiReorder::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - UChar *ustr, *ustr2; - if ((unsigned long)key < 2) // hack, we're en(1)/de(0)ciphering - return -1; - - int32_t len = text.length(); - ustr = new UChar[len]; //each char could become a surrogate pair - - // Convert UTF-8 string to UTF-16 (UChars) - len = ucnv_toUChars(conv, ustr, len, text.c_str(), -1, &err); - ustr2 = new UChar[len]; - - UBiDi* bidi = ubidi_openSized(len + 1, 0, &err); - ubidi_setPara(bidi, ustr, len, UBIDI_DEFAULT_RTL, NULL, &err); - len = ubidi_writeReordered(bidi, ustr2, len, - UBIDI_DO_MIRRORING | UBIDI_REMOVE_BIDI_CONTROLS, &err); - ubidi_close(bidi); - -// len = ubidi_writeReverse(ustr, len, ustr2, len, -// UBIDI_DO_MIRRORING | UBIDI_REMOVE_BIDI_CONTROLS, &err); - - text.setSize(text.size()*2); - len = ucnv_fromUChars(conv, text.getRawData(), text.size(), ustr2, len, &err); - text.setSize(len); - - delete [] ustr2; - delete [] ustr; - return 0; -} - -SWORD_NAMESPACE_END -#endif diff --git a/src/modules/filters/utf8cantillation.cpp b/src/modules/filters/utf8cantillation.cpp deleted file mode 100644 index 6213620..0000000 --- a/src/modules/filters/utf8cantillation.cpp +++ /dev/null @@ -1,55 +0,0 @@ -/****************************************************************************** - * - * UTF8Cantillation - SWFilter descendant to remove UTF-8 Hebrew cantillation - * - */ - - -#include -#include -#include - -SWORD_NAMESPACE_START - -const char oName[] = "Hebrew Cantillation"; -const char oTip[] = "Toggles Hebrew Cantillation Marks"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -UTF8Cantillation::UTF8Cantillation() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("Off"); -} - - -UTF8Cantillation::~UTF8Cantillation(){}; - - -char UTF8Cantillation::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - if (!option) { - //The UTF-8 range 0xD6 0x90 to 0xD6 0xAF and 0xD7 0x84 consist of Hebrew cantillation marks so block those out. - SWBuf orig = text; - const unsigned char* from = (unsigned char*)orig.c_str(); - for (text = ""; *from; from++) { - if (*from != 0xD6) { - if (*from == 0xD7 && *(from + 1) == 0x84) { - from++; - } - else { - text += *from; - } - } - else if (*(from + 1) < 0x90 || *(from + 1) > 0xAF) { - text += *from; - from++; - text += *from; - } - else { - from++; - } - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/utf8greekaccents.cpp b/src/modules/filters/utf8greekaccents.cpp deleted file mode 100644 index 05ef59b..0000000 --- a/src/modules/filters/utf8greekaccents.cpp +++ /dev/null @@ -1,249 +0,0 @@ -/****************************************************************************** - * - * UTF8GreekAccents - SWFilter descendant to remove UTF-8 Greek accents - * - */ - - -#include -#include -#include - -SWORD_NAMESPACE_START - -const char oName[] = "Greek Accents"; -const char oTip[] = "Toggles Greek Accents"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -UTF8GreekAccents::UTF8GreekAccents() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("On"); -} - -UTF8GreekAccents::~UTF8GreekAccents(){}; - - -char UTF8GreekAccents::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - - if (!option) { //we don't want greek accents - //unsigned char *to, *from; - //to = (unsigned char*)text; - //for (from = (unsigned char*)text; *from; from++) { - - SWBuf orig = text; - const unsigned char* from = (unsigned char*)orig.c_str(); - for (text = ""; *from; from++) { - //first just remove combining characters - if (*from == 0xE2 && *(from + 1) == 0x80 && *(from + 2) == 0x99) { - from += 2; - } - else if (*from == 0xCC && *(from + 1)) { - if (*(from + 1) == 0x80 || *(from + 1) == 0x81 || *(from + 1) == 0x82 || *(from + 1) == 0x88 || *(from + 1) == 0x93 || *(from + 1) == 0x94) { - from++; - } - } - else if (*from == 0xCD && *(from + 1) == 0xBA) { - from++; - } - //now converted pre-composed characters to their alphabetic bases, discarding the accents - - //Greek - //capital alpha - else if ((*from == 0xCE && *(from + 1) == 0x86)) { - text += 0xCE; - text += 0x91; - from++; - } - //capital epsilon - else if ((*from == 0xCE && *(from + 1) == 0x88)) { - text += 0xCE; - text += 0x95; - from++; - } - //capital eta - else if ((*from == 0xCE && *(from + 1) == 0x89)) { - text += 0xCE; - text += 0x97; - from++; - } - //capital iota - else if ((*from == 0xCE && (*(from + 1) == 0x8A || *(from + 1) == 0xAA))) { - text += 0xCE; - text += 0x99; - from++; - } - //capital omicron - else if ((*from == 0xCE && *(from + 1) == 0x8C)) { - text += 0xCE; - text += 0x9F; - from++; - } - //capital upsilon - else if ((*from == 0xCE && (*(from + 1) == 0x8E || *(from + 1) == 0xAB))) { - text += 0xCE; - text += 0xA5; - from++; - } - //capital omega - else if ((*from == 0xCE && *(from + 1) == 0x8F)) { - text += 0xCE; - text += 0xA9; - from++; - } - - //alpha - else if ((*from == 0xCE && *(from + 1) == 0xAC)) { - text += 0xCE; - text += 0xB1; - from++; - } - //epsilon - else if ((*from == 0xCE && *(from + 1) == 0xAD)) { - text += 0xCE; - text += 0xB5; - from++; - } - //eta - else if ((*from == 0xCE && *(from + 1) == 0xAE)) { - text += 0xCE; - text += 0xB7; - from++; - } - //iota - else if ((*from == 0xCE && *(from + 1) == 0xAF) || (*from == 0xCF && *(from + 1) == 0x8A)) { - text += 0xCE; - text += 0xB9; - from++; - } - //omicron - else if ((*from == 0xCF && *(from + 1) == 0x8C)) { - text += 0xCE; - text += 0xBF; - from++; - } - //upsilon - else if ((*from == 0xCE && *(from + 1) == 0x88) || (*from == 0xCF && (*(from + 1) == 0x8B || *(from + 1) == 0x8D))) { - text += 0xCF; - text += 0x85; - from++; - } - //omega - else if ((*from == 0xCF && *(from + 1) == 0x8E)) { - text += 0xCF; - text += 0x89; - from++; - } - - //Extended Greek - //capital alpha - else if (*from == 0xE1 && ((*(from + 1) == 0xBC || *(from + 1) == 0xBE) && *(from + 2) >= 0x88 && *(from + 2) <= 0x8F) || (*(from + 1) == 0xBE && *(from + 2) >= 0xB8 && *(from + 2) <= 0xBC)) { - text += 0xCE; - text += 0x91; - from+=2; - } - //capital epsilon - else if (*from == 0xE1 && ((*(from + 1) == 0xBC && *(from + 2) >= 0x98 && *(from + 2) <= 0x9D) || (*(from + 1) == 0xBF && (*(from + 2) == 0x88 || *(from + 2) == 0x89)))) { - text += 0xCE; - text += 0x95; - from+=2; - } - //capital eta - else if (*from == 0xE1 && ((*(from + 1) == 0xBC && *(from + 2) >= 0xA8 && *(from + 2) <= 0xAF) || (*(from + 1) == 0xBE && *(from + 2) >= 0x98 && *(from + 2) <= 0x9F) || (*(from + 1) == 0xBF && *(from + 2) >= 0x8A && *(from + 2) <= 0x8C))) { - text += 0xCE; - text += 0x97; - from+=2; - } - //capital iota - else if (*from == 0xE1 && ((*(from + 1) == 0xBC && *(from + 2) >= 0xB8 && *(from + 2) <= 0xBF) || (*(from + 1) == 0xBF && *(from + 2) >= 0x98 && *(from + 2) <= 0x9B))) { - text += 0xCE; - text += 0x99; - from+=2; - } - //capital omicron - else if (*from == 0xE1 && ((*(from + 1) == 0xBD && *(from + 2) >= 0x88 && *(from + 2) <= 0x8D) || (*(from + 1) == 0xBF && *(from + 2) == 0xB8 || *(from + 2) == 0xB9))) { - text += 0xCE; - text += 0x9F; - from+=2; - } - //capital upsilon - else if (*from == 0xE1 && ((*(from + 1) == 0xBD && *(from + 2) >= 0x99 && *(from + 2) <= 0x9F) || (*(from + 1) == 0xBF && *(from + 2) >= 0xA8 && *(from + 2) <= 0xAB))) { - text += 0xCE; - text += 0xA5; - from+=2; - } - //capital omega - else if (*from == 0xE1 && (((*(from + 1) == 0xBD || *(from + 1) == 0xBE) && *(from + 2) >= 0xA8 && *(from + 2) <= 0xAF) || (*(from + 1) == 0xBF && *(from + 2) >= 0xBA && *(from + 2) <= 0xBC))) { - text += 0xCE; - text += 0xA9; - from+=2; - } - //capital rho - else if (*from == 0xE1 && *(from + 1) == 0xBF && *(from + 2) == 0xAC) { - text += 0xCE; - text += 0xA1; - from+=2; - } - - //alpha - else if (*from == 0xE1 && ((*(from + 1) == 0xBC || *(from + 1) == 0xBE) && *(from + 2) >= 0x80 && *(from + 2) <= 0x87) || (*(from + 1) == 0xBD && (*(from + 2) == 0xB0 || *(from + 2) == 0xB1)) || (*(from + 1) == 0xBE && *(from + 2) >= 0xB0 && *(from + 2) <= 0xB7)) { - text += 0xCE; - text += 0xB1; - from+=2; - } - //epsilon - else if (*from == 0xE1 && ((*(from + 1) == 0xBC && *(from + 2) >= 0x90 && *(from + 2) <= 0x95) || (*(from + 1) == 0xBD && (*(from + 2) == 0xB2 || *(from + 2) == 0xB3)))) { - text += 0xCE; - text += 0xB5; - from+=2; - } - //eta - else if (*from == 0xE1 && ((*(from + 1) == 0xBE && *(from + 2) >= 0x90 && *(from + 2) <= 0x97) || (*(from + 1) == 0xBC && *(from + 2) >= 0xA0 && *(from + 2) <= 0xA7) || (*(from + 1) == 0xBF && *(from + 2) >= 0x82 && *(from + 2) <= 0x87) || (*(from + 1) == 0xBD && (*(from + 2) == 0xB4 || *(from + 2) == 0xB5)))) { - text += 0xCE; - text += 0xB7; - from+=2; - } - //iota - else if (*from == 0xE1 && ((*(from + 1) == 0xBC && *(from + 2) >= 0xB0 && *(from + 2) <= 0xB7) || (*(from + 1) == 0xBD && (*(from + 2) == 0xB6 || *(from + 2) == 0xB7)) || (*(from + 1) == 0xBF && *(from + 2) >= 0x90 && *(from + 2) <= 0x97))) { - text += 0xCE; - text += 0xB9; - from+=2; - } - //omicron - else if (*from == 0xE1 && (*(from + 1) == 0xBD && ((*(from + 2) >= 0x80 && *(from + 2) <= 0x85) || (*(from + 2) == 0xB8 || *(from + 2) == 0xB9)))) { - text += 0xCE; - text += 0xBF; - from+=2; - } - //upsilon - else if (*from == 0xE1 && ((*(from + 1) == 0xBD && ((*(from + 2) >= 0x90 && *(from + 2) <= 0x97) || *(from + 2) == 0xBA || *(from + 2) == 0xBB)) || (*(from + 1) == 0xBF && ((*(from + 2) >= 0xA0 && *(from + 2) <= 0xA3) || *(from + 2) == 0xA6 || *(from + 2) == 0xA7)))) { - text += 0xCF; - text += 0x85; - from+=2; - } - //omega - else if (*from == 0xE1 && ((*(from + 1) == 0xBD && ((*(from + 2) >= 0xA0 && *(from + 2) <= 0xA7) || (*(from + 2) == 0xBC || *(from + 2) == 0xBD))) || (*(from + 1) == 0xBE && (*(from + 2) >= 0xA0 && *(from + 2) <= 0xA7)) || (*(from + 1) == 0xBF && *(from + 2) >= 0xB2 && *(from + 2) <= 0xB7))) { - text += 0xCF; - text += 0x89; - from+=2; - } - //rho - else if (*from == 0xE1 && *(from + 1) == 0xBF && (*(from + 2) == 0xA4 && *(from + 2) == 0xA5)) { - text += 0xCF; - text += 0x81; - from+=2; - } - else { //no characters we filter - text += *from; - } - } - } - return 0; -} - - - - - - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/utf8hebrewpoints.cpp b/src/modules/filters/utf8hebrewpoints.cpp deleted file mode 100644 index 0476db8..0000000 --- a/src/modules/filters/utf8hebrewpoints.cpp +++ /dev/null @@ -1,44 +0,0 @@ -/****************************************************************************** - * - * UTF8HebrewPoints - SWFilter descendant to remove UTF-8 Hebrew vowel points - * - */ - - -#include -#include -#include - -SWORD_NAMESPACE_START - -const char oName[] = "Hebrew Vowel Points"; -const char oTip[] = "Toggles Hebrew Vowel Points"; - -const SWBuf choices[3] = {"On", "Off", ""}; -const StringList oValues(&choices[0], &choices[2]); - -UTF8HebrewPoints::UTF8HebrewPoints() : SWOptionFilter(oName, oTip, &oValues) { - setOptionValue("On"); -} - -UTF8HebrewPoints::~UTF8HebrewPoints(){}; - - -char UTF8HebrewPoints::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - if (!option) { - //The UTF-8 range 0xD6 0xB0 to 0xD6 0xBF excluding 0xD6 0x consist of Hebrew cantillation marks so block those out. - SWBuf orig = text; - const unsigned char* from = (unsigned char*)orig.c_str(); - for (text = ""; *from; from++) { - if ((*from == 0xD6) && (*(from + 1) >= 0xB0 && *(from + 1) <= 0xBF) && (*(from + 1) != 0xBE)) { - from++; - } - else { - text += *from; - } - } - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/utf8html.cpp b/src/modules/filters/utf8html.cpp deleted file mode 100644 index 94fbdc1..0000000 --- a/src/modules/filters/utf8html.cpp +++ /dev/null @@ -1,69 +0,0 @@ -/****************************************************************************** - * - * utf8html - SWFilter descendant to convert a UTF-8 stream to HTML escapes - * - */ - - -#include -#include -#include - -SWORD_NAMESPACE_START - -UTF8HTML::UTF8HTML() { -} - - -char UTF8HTML::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - unsigned char *from; - int len; - char digit[10]; - unsigned long ch; - if ((unsigned long)key < 2) // hack, we're en(1)/de(0)ciphering - return -1; - - len = strlenw(text.c_str()) + 2; // shift string to right of buffer - - SWBuf orig = text; - from = (unsigned char *)orig.c_str(); - - // ------------------------------- - for (text = ""; *from; from++) { - ch = 0; - if ((*from & 128) != 128) { -// if (*from != ' ') - text += *from; - continue; - } - if ((*from & 128) && ((*from & 64) != 64)) { - // error - *from = 'x'; - continue; - } - *from <<= 1; - int subsequent; - for (subsequent = 1; (*from & 128); subsequent++) { - *from <<= 1; - from[subsequent] &= 63; - ch <<= 6; - ch |= from[subsequent]; - } - subsequent--; - *from <<=1; - char significantFirstBits = 8 - (2+subsequent); - - ch |= (((short)*from) << (((6*subsequent)+significantFirstBits)-8)); - from += subsequent; - text += '&'; - text += '#'; - sprintf(digit, "%d", ch); - for (char *dig = digit; *dig; dig++) - text += *dig; - text += ';'; - } - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/filters/utf8latin1.cpp b/src/modules/filters/utf8latin1.cpp deleted file mode 100644 index 6ab4c9c..0000000 --- a/src/modules/filters/utf8latin1.cpp +++ /dev/null @@ -1,74 +0,0 @@ -/****************************************************************************** - * - * UTF8Latin1 - SWFilter descendant to convert UTF-8 to Latin-1 - * - */ - -#include -#include - -#include - -SWORD_NAMESPACE_START - -UTF8Latin1::UTF8Latin1(char rchar) : replacementChar(rchar) { -} - - -char UTF8Latin1::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - unsigned char *from; - - int len; - unsigned long uchar; - unsigned char significantFirstBits, subsequent; - - if ((unsigned long)key < 2) {// hack, we're en(1)/de(0)ciphering - return -1; - } - len = strlen(text.c_str()) + 1; // shift string to right of buffer - - SWBuf orig = text; - from = (unsigned char*)orig.c_str(); - - - // ------------------------------- - - for (text = ""; *from; from++) { - uchar = 0; - if ((*from & 128) != 128) { - // if (*from != ' ') - uchar = *from; - } - else if ((*from & 128) && ((*from & 64) != 64)) { - // error, do nothing - continue; - } - else { - *from <<= 1; - for (subsequent = 1; (*from & 128); subsequent++) { - *from <<= 1; - from[subsequent] &= 63; - uchar <<= 6; - uchar |= from[subsequent]; - } - subsequent--; - *from <<=1; - significantFirstBits = 8 - (2+subsequent); - - uchar |= (((short)*from) << (((6*subsequent)+significantFirstBits)-8)); - from += subsequent; - } - - if (uchar < 0xff) { - text += (unsigned char)uchar; - } - else { - text += replacementChar; - } - } - return 0; -} - -SWORD_NAMESPACE_END - diff --git a/src/modules/filters/utf8nfc.cpp b/src/modules/filters/utf8nfc.cpp deleted file mode 100644 index 5500224..0000000 --- a/src/modules/filters/utf8nfc.cpp +++ /dev/null @@ -1,53 +0,0 @@ -/****************************************************************************** -* -* utf8nfc - SWFilter descendant to perform NFC (canonical composition -* normalization) on UTF-8 text -*/ - -#ifdef _ICU_ - -#include - -#ifdef __GNUC__ -#include -#endif - -#include - -SWORD_NAMESPACE_START - -UTF8NFC::UTF8NFC() { - conv = ucnv_open("UTF-8", &err); -} - -UTF8NFC::~UTF8NFC() { - ucnv_close(conv); -} - -char UTF8NFC::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - if ((unsigned long)key < 2) // hack, we're en(1)/de(0)ciphering - return -1; - - int32_t len = text.length() * 2; - source = new UChar[len + 1]; //each char could become a surrogate pair - - // Convert UTF-8 string to UTF-16 (UChars) - len = ucnv_toUChars(conv, source, len, text.c_str(), -1, &err); - target = new UChar[len + 1]; - - //canonical composition - unorm_normalize(source, len, UNORM_NFC, 0, target, len, &err); - - text.setSize(text.size()*2); - len = ucnv_fromUChars(conv, text.getRawData(), text.size(), target, -1, &err); - text.setSize(len); - - delete [] source; - delete [] target; - - return 0; -} - -SWORD_NAMESPACE_END -#endif diff --git a/src/modules/filters/utf8nfkd.cpp b/src/modules/filters/utf8nfkd.cpp deleted file mode 100644 index 6da24f8..0000000 --- a/src/modules/filters/utf8nfkd.cpp +++ /dev/null @@ -1,53 +0,0 @@ -/****************************************************************************** -* -* utf8nfkd - SWFilter descendant to perform NFKD (compatability decomposition -* normalization) on UTF-8 text -*/ - -#ifdef _ICU_ - -#include - -#ifdef __GNUC__ -#include -#endif - -#include - -SWORD_NAMESPACE_START - -UTF8NFKD::UTF8NFKD() { - conv = ucnv_open("UTF-8", &err); -} - -UTF8NFKD::~UTF8NFKD() { - ucnv_close(conv); -} - -char UTF8NFKD::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - if ((unsigned long)key < 2) // hack, we're en(1)/de(0)ciphering - return -1; - - int32_t len = text.length() * 2; - source = new UChar[len + 1]; //each char could become a surrogate pair - - // Convert UTF-8 string to UTF-16 (UChars) - len = ucnv_toUChars(conv, source, len, text.c_str(), -1, &err); - target = new UChar[len + 1]; - - //compatability decomposition - unorm_normalize(source, len, UNORM_NFKD, 0, target, len, &err); - - text.setSize(text.size()*2); - len = ucnv_fromUChars(conv, text.getRawData(), text.size(), target, -1, &err); - text.setSize(len); - - delete [] source; - delete [] target; - - return 0; -} - -SWORD_NAMESPACE_END -#endif diff --git a/src/modules/filters/utf8transliterator.cpp b/src/modules/filters/utf8transliterator.cpp deleted file mode 100644 index b753c0c..0000000 --- a/src/modules/filters/utf8transliterator.cpp +++ /dev/null @@ -1,889 +0,0 @@ -/****************************************************************************** -* -* utf8transliterators - SWFilter descendant to transliterate between -* ICU-supported scripts. -*/ - -#ifdef _ICU_ - -#include - -#ifdef __GNUC__ -#include -#endif - -#include -#include -#include - -#ifndef _ICUSWORD_ -#include "unicode/resbund.h" -#endif -#include - -SWORD_NAMESPACE_START - -const char UTF8Transliterator::optionstring[NUMTARGETSCRIPTS][16] = { - "Off", - "Latin", - "IPA", - "Basic Latin", - "SBL", - "TC", - "Beta", - "BGreek", - "SERA", - "Hugoye", - "UNGEGN", - "ISO", - "ALA-LC", - "BGN-PCGN", - "Greek", - "Hebrew", - "Cyrillic", - "Arabic", - "Syriac", - "Katakana", - "Hiragana", - "Hangul", - "Devanagari", - "Tamil", - "Bengali", - "Gurmukhi", - "Gujarati", - "Oriya", - "Telugu", - "Kannada", - "Malayalam", - "Thai", - "Georgian", - "Armenian", - "Ethiopic", - "Gothic", - "Ugaritic", - "Coptic", - "Meroitic", - "Linear B", - "Cypriot", - "Runic", - "Ogham", - "Thaana", - "Glagolitic", - "Tengwar", - "Cirth" -}; - -const char UTF8Transliterator::optName[] = "Transliteration"; -const char UTF8Transliterator::optTip[] = "Transliterates between scripts"; - -SWTransMap UTF8Transliterator::transMap; - -#ifndef _ICUSWORD_ - -const char UTF8Transliterator::SW_RB_RULE_BASED_IDS[] = "RuleBasedTransliteratorIDs"; -const char UTF8Transliterator::SW_RB_RULE[] = "Rule"; -#ifdef SWICU_DATA -const char UTF8Transliterator::SW_RESDATA[] = SWICU_DATA; -#else -const char UTF8Transliterator::SW_RESDATA[] = "/usr/local/lib/sword/"; -#endif - -class SWCharString { - public: - inline SWCharString(const UnicodeString& str); - inline ~SWCharString(); - inline operator const char*() { return ptr; } - private: - char buf[128]; - char* ptr; -}; -SWCharString::SWCharString(const UnicodeString& str) { - // TODO This isn't quite right -- we should probably do - // preflighting here to determine the real length. - if (str.length() >= (int32_t)sizeof(buf)) { - ptr = new char[str.length() + 8]; - } else { - ptr = buf; - } - str.extract(0, 0x7FFFFFFF, ptr, ""); -} - -SWCharString::~SWCharString() { - if (ptr != buf) { - delete[] ptr; - } -} - -#endif // _ICUSWORD_ - - -UTF8Transliterator::UTF8Transliterator() { - option = 0; - unsigned long i; - for (i = 0; i < NUMTARGETSCRIPTS; i++) { - options.push_back(optionstring[i]); - } -#ifndef _ICUSWORD_ - utf8status = U_ZERO_ERROR; - Load(utf8status); -#endif -} - -void UTF8Transliterator::Load(UErrorCode &status) -{ -#ifndef _ICUSWORD_ - static const char translit_swordindex[] = "translit_swordindex"; - - UResourceBundle *bundle, *transIDs, *colBund; - bundle = ures_openDirect(SW_RESDATA, translit_swordindex, &status); - if (U_FAILURE(status)) { - SWLog::systemlog->LogError("no resource index to load"); - SWLog::systemlog->LogError("status %s", u_errorName(status)); - return; - } - - transIDs = ures_getByKey(bundle, SW_RB_RULE_BASED_IDS, 0, &status); - UParseError parseError; - - int32_t row, maxRows; - if (U_SUCCESS(status)) { - maxRows = ures_getSize(transIDs); - for (row = 0; row < maxRows; row++) { - colBund = ures_getByIndex(transIDs, row, 0, &status); - - if (U_SUCCESS(status) && ures_getSize(colBund) == 4) { - UnicodeString id = ures_getUnicodeStringByIndex(colBund, 0, &status); - UChar type = ures_getUnicodeStringByIndex(colBund, 1, &status).charAt(0); - UnicodeString resString = ures_getUnicodeStringByIndex(colBund, 2, &status); - SWLog::systemlog->LogInformation("ok so far"); - - if (U_SUCCESS(status)) { - switch (type) { - case 0x66: // 'f' - case 0x69: // 'i' - // 'file' or 'internal'; - // row[2]=resource, row[3]=direction - { - UBool visible = (type == 0x0066 /*f*/); - UTransDirection dir = - (ures_getUnicodeStringByIndex(colBund, 3, &status).charAt(0) == - 0x0046 /*F*/) ? - UTRANS_FORWARD : UTRANS_REVERSE; - //registry->put(id, resString, dir, visible); - SWLog::systemlog->LogInformation("instantiating %s ...", resString.getBuffer()); - registerTrans(id, resString, dir, status); - SWLog::systemlog->LogInformation("done."); - } - break; - case 0x61: // 'a' - // 'alias'; row[2]=createInstance argument - //registry->put(id, resString, TRUE); - break; - } - } - else SWLog::systemlog->LogError("Failed to get resString"); - } - else SWLog::systemlog->LogError("Failed to get row"); - ures_close(colBund); - } - } - else - { - SWLog::systemlog->LogError("no resource index to load"); - SWLog::systemlog->LogError("status %s", u_errorName(status)); - } - - ures_close(transIDs); - ures_close(bundle); - -#endif // _ICUSWORD_ -} - -void UTF8Transliterator::registerTrans(const UnicodeString& ID, const UnicodeString& resource, - UTransDirection dir, UErrorCode &status ) -{ -#ifndef _ICUSWORD_ - SWLog::systemlog->LogInformation("registering ID locally %s", ID.getBuffer()); - SWTransData swstuff; - swstuff.resource = resource; - swstuff.dir = dir; - SWTransPair swpair; - swpair.first = ID; - swpair.second = swstuff; - transMap.insert(swpair); -#endif -} - -bool UTF8Transliterator::checkTrans(const UnicodeString& ID, UErrorCode &status ) -{ -#ifndef _ICUSWORD_ - Transliterator *trans = Transliterator::createInstance(ID, UTRANS_FORWARD, status); - if (!U_FAILURE(status)) - { - // already have it, clean up and return true - SWLog::systemlog->LogInformation("already have it %s", ID.getBuffer()); - delete trans; - return true; - } - status = U_ZERO_ERROR; - - SWTransMap::iterator swelement; - if ((swelement = transMap.find(ID)) != transMap.end()) - { - SWLog::systemlog->LogInformation("found element in map"); - SWTransData swstuff = (*swelement).second; - UParseError parseError; - //UErrorCode status; - //std::cout << "unregistering " << ID << std::endl; - //Transliterator::unregister(ID); - SWLog::systemlog->LogInformation("resource is %s", swstuff.resource.getBuffer()); - - // Get the rules - //std::cout << "importing: " << ID << ", " << resource << std::endl; - SWCharString ch(swstuff.resource); - UResourceBundle *bundle = ures_openDirect(SW_RESDATA, ch, &status); - const UnicodeString rules = ures_getUnicodeStringByKey(bundle, SW_RB_RULE, &status); - ures_close(bundle); - //parser.parse(rules, isReverse ? UTRANS_REVERSE : UTRANS_FORWARD, - // parseError, status); - if (U_FAILURE(status)) { - SWLog::systemlog->LogError("Failed to get rules"); - SWLog::systemlog->LogError("status %s", u_errorName(status)); - return false; - } - - - Transliterator *trans = Transliterator::createFromRules(ID, rules, swstuff.dir, - parseError,status); - if (U_FAILURE(status)) { - SWLog::systemlog->LogError("Failed to create transliterator"); - SWLog::systemlog->LogError("status %s", u_errorName(status)); - SWLog::systemlog->LogError("Parse error: line %s", parseError.line); - SWLog::systemlog->LogError("Parse error: offset %d", parseError.offset); - SWLog::systemlog->LogError("Parse error: preContext %s", *parseError.preContext); - SWLog::systemlog->LogError("Parse error: postContext %s", *parseError.postContext); - SWLog::systemlog->LogError("rules were"); -// SWLog::systemlog->LogError((const char *)rules); - return false; - } - - Transliterator::registerInstance(trans); - return true; - - //Transliterator *trans = instantiateTrans(ID, swstuff.resource, swstuff.dir, parseError, status); - //return trans; - } - else - { - return false; - } -#else -return true; -#endif // _ICUSWORD_ -} - -bool UTF8Transliterator::addTrans(const char* newTrans, SWBuf* transList) { -#ifdef _ICUSWORD_ - UErrorCode status; - if (checkTrans(UnicodeString(newTrans), status)) { -#endif - *transList += newTrans; - *transList += ";"; - return true; -#ifdef _ICUSWORD_ - } - else { - return false; - } -#endif -} - -Transliterator * UTF8Transliterator::createTrans(const UnicodeString& ID, UTransDirection dir, UErrorCode &status ) -{ - Transliterator *trans = Transliterator::createInstance(ID,UTRANS_FORWARD,status); - if (U_FAILURE(status)) { - delete trans; - return NULL; - } - else { - return trans; - } -} - -void UTF8Transliterator::setOptionValue(const char *ival) -{ - unsigned char i = option = NUMTARGETSCRIPTS; - while (i && stricmp(ival, optionstring[i])) { - i--; - option = i; - } -} - -const char *UTF8Transliterator::getOptionValue() -{ - return (NUMTARGETSCRIPTS > option) ? optionstring[option] : 0; -} - -char UTF8Transliterator::processText(SWBuf &text, const SWKey *key, const SWModule *module) -{ - if (option) { // if we want transliteration - unsigned long i, j; - UErrorCode err = U_ZERO_ERROR; - UConverter * conv = NULL; - conv = ucnv_open("UTF-8", &err); - SWBuf ID; - - bool compat = false; - - // Convert UTF-8 string to UTF-16 (UChars) - j = strlen(text); - int32_t len = (j * 2) + 1; - UChar *source = new UChar[len]; - err = U_ZERO_ERROR; - len = ucnv_toUChars(conv, source, len, text, j, &err); - source[len] = 0; - - // Figure out which scripts are used in the string - unsigned char scripts[NUMSCRIPTS]; - - for (i = 0; i < NUMSCRIPTS; i++) { - scripts[i] = false; - } - - for (i = 0; i < len; i++) { - j = ublock_getCode(source[i]); - scripts[SE_LATIN] = true; - switch (j) { - //case UBLOCK_BASIC_LATIN: scripts[SE_LATIN] = true; break; - case UBLOCK_GREEK: scripts[SE_GREEK] = true; break; - case UBLOCK_HEBREW: scripts[SE_HEBREW] = true; break; - case UBLOCK_CYRILLIC: scripts[SE_CYRILLIC] = true; break; - case UBLOCK_ARABIC: scripts[SE_ARABIC] = true; break; - case UBLOCK_SYRIAC: scripts[SE_SYRIAC] = true; break; - case UBLOCK_KATAKANA: scripts[SE_KATAKANA] = true; break; - case UBLOCK_HIRAGANA: scripts[SE_HIRAGANA] = true; break; - case UBLOCK_HANGUL_SYLLABLES: scripts[SE_HANGUL] = true; break; - case UBLOCK_HANGUL_JAMO: scripts[SE_JAMO] = true; break; - case UBLOCK_DEVANAGARI: scripts[SE_DEVANAGARI] = true; break; - case UBLOCK_TAMIL: scripts[SE_TAMIL] = true; break; - case UBLOCK_BENGALI: scripts[SE_BENGALI] = true; break; - case UBLOCK_GURMUKHI: scripts[SE_GURMUKHI] = true; break; - case UBLOCK_GUJARATI: scripts[SE_GUJARATI] = true; break; - case UBLOCK_ORIYA: scripts[SE_ORIYA] = true; break; - case UBLOCK_TELUGU: scripts[SE_TELUGU] = true; break; - case UBLOCK_KANNADA: scripts[SE_KANNADA] = true; break; - case UBLOCK_MALAYALAM: scripts[SE_MALAYALAM] = true; break; - case UBLOCK_THAI: scripts[SE_THAI] = true; break; - case UBLOCK_GEORGIAN: scripts[SE_GEORGIAN] = true; break; - case UBLOCK_ARMENIAN: scripts[SE_ARMENIAN] = true; break; - case UBLOCK_ETHIOPIC: scripts[SE_ETHIOPIC] = true; break; - case UBLOCK_GOTHIC: scripts[SE_GOTHIC] = true; break; - case UBLOCK_UGARITIC: scripts[SE_UGARITIC] = true; break; -// case UBLOCK_MEROITIC: scripts[SE_MEROITIC] = true; break; -// case UBLOCK_LINEARB: scripts[SE_LINEARB] = true; break; -// case UBLOCK_CYPRIOT: scripts[SE_CYPRIOT] = true; break; - case UBLOCK_RUNIC: scripts[SE_RUNIC] = true; break; - case UBLOCK_OGHAM: scripts[SE_OGHAM] = true; break; - case UBLOCK_THAANA: scripts[SE_THAANA] = true; break; -// case UBLOCK_GLAGOLITIC: scripts[SE_GLAGOLITIC] = true; break; -// case UBLOCK_TENGWAR: scripts[SE_TENGWAR] = true; break; -// case UBLOCK_CIRTH: scripts[SE_CIRTH] = true; break; - case UBLOCK_CJK_RADICALS_SUPPLEMENT: - case UBLOCK_KANGXI_RADICALS: - case UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS: - case UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION: - case UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A: - case UBLOCK_CJK_UNIFIED_IDEOGRAPHS: - scripts[SE_HAN] = true; - break; - case UBLOCK_CJK_COMPATIBILITY: - case UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS: - case UBLOCK_CJK_COMPATIBILITY_FORMS: - scripts[SE_HAN] = true; - compat = true; - break; - case UBLOCK_HANGUL_COMPATIBILITY_JAMO: - scripts[SE_HANGUL] = true; - compat = true; - break; - - //default: scripts[SE_LATIN] = true; - } - } - scripts[option] = false; //turn off the reflexive transliteration - - //return if we have no transliteration to do for this text - j = 0; - for (i = 0; !j && i < NUMSCRIPTS; i++) { - if (scripts[i]) j++; - } - if (!j) { - ucnv_close(conv); - return 0; - } - - if (compat) { - addTrans("NFKD", &ID); - } - else { - addTrans("NFD", &ID); - } - - //Simple X to Latin transliterators - if (scripts[SE_GREEK]) { - if (strnicmp (((SWModule*)module)->Lang(), "cop", 3)) { - if (option == SE_SBL) - addTrans("Greek-Latin/SBL", &ID); - else if (option == SE_TC) - addTrans("Greek-Latin/TC", &ID); - else if (option == SE_BETA) - addTrans("Greek-Latin/Beta", &ID); - else if (option == SE_BGREEK) - addTrans("Greek-Latin/BGreek", &ID); - else if (option == SE_UNGEGN) - addTrans("Greek-Latin/UNGEGN", &ID); - else if (option == SE_ISO) - addTrans("Greek-Latin/ISO", &ID); - else if (option == SE_ALALC) - addTrans("Greek-Latin/ALALC", &ID); - else if (option == SE_BGNPCGN) - addTrans("Greek-Latin/BGNPCGN", &ID); - else if (option == SE_IPA) - addTrans("Greek-IPA/Ancient", &ID); - else { - addTrans("Greek-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - else { - if (option == SE_SBL) - addTrans("Coptic-Latin/SBL", &ID); - else if (option == SE_TC) - addTrans("Coptic-Latin/TC", &ID); - else if (option == SE_BETA) - addTrans("Coptic-Latin/Beta", &ID); - else if (option == SE_IPA) - addTrans("Coptic-IPA", &ID); - else { - addTrans("Coptic-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - } - if (scripts[SE_HEBREW]) { - if (option == SE_SBL) - addTrans("Hebrew-Latin/SBL", &ID); - else if (option == SE_TC) - addTrans("Hebrew-Latin/TC", &ID); - else if (option == SE_BETA) - addTrans("Hebrew-Latin/Beta", &ID); - else if (option == SE_UNGEGN) - addTrans("Hebrew-Latin/UNGEGN", &ID); - else if (option == SE_ALALC) - addTrans("Hebrew-Latin/ALALC", &ID); - else if (option == SE_SYRIAC) - addTrans("Hebrew-Syriac", &ID); - else { - addTrans("Hebrew-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - if (scripts[SE_CYRILLIC]) { - if (option == SE_GLAGOLITIC) - addTrans("Cyrillic-Glagolitic", &ID); - else { - addTrans("Cyrillic-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - if (scripts[SE_ARABIC]) { - addTrans("Arabic-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_SYRIAC]) { - if (option == SE_TC) - addTrans("Syriac-Latin/TC", &ID); - else if (option == SE_BETA) - addTrans("Syriac-Latin/Beta", &ID); - else if (option == SE_HUGOYE) - addTrans("Syriac-Latin/Hugoye", &ID); - else if (option == SE_HEBREW) - addTrans("Syriac-Hebrew", &ID); - else { - addTrans("Syriac-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - if (scripts[SE_THAI]) { - addTrans("Thai-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_GEORGIAN]) { - if (option == SE_ISO) - addTrans("Georgian-Latin/ISO", &ID); - else if (option == SE_ALALC) - addTrans("Georgian-Latin/ALALC", &ID); - else if (option == SE_BGNPCGN) - addTrans("Georgian-Latin/BGNPCGN", &ID); - else if (option == SE_IPA) - addTrans("Georgian-IPA", &ID); - else { - addTrans("Georgian-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - if (scripts[SE_ARMENIAN]) { - if (option == SE_ISO) - addTrans("Armenian-Latin/ISO", &ID); - else if (option == SE_ALALC) - addTrans("Armenian-Latin/ALALC", &ID); - else if (option == SE_BGNPCGN) - addTrans("Armenian-Latin/BGNPCGN", &ID); - else if (option == SE_IPA) - addTrans("Armenian-IPA", &ID); - else { - addTrans("Armenian-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - if (scripts[SE_ETHIOPIC]) { - if (option == SE_UNGEGN) - addTrans("Ethiopic-Latin/UNGEGN", &ID); - else if (option == SE_ISO) - addTrans("Ethiopic-Latin/ISO", &ID); - else if (option == SE_ALALC) - addTrans("Ethiopic-Latin/ALALC", &ID); - else if (option == SE_SERA) - addTrans("Ethiopic-Latin/SERA", &ID); - else { - addTrans("Ethiopic-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - if (scripts[SE_GOTHIC]) { - if (option == SE_BASICLATIN) - addTrans("Gothic-Latin/Basic", &ID); - else if (option == SE_IPA) - addTrans("Gothic-IPA", &ID); - else { - addTrans("Gothic-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - if (scripts[SE_UGARITIC]) { - if (option == SE_SBL) - addTrans("Ugaritic-Latin/SBL", &ID); - else { - addTrans("Ugaritic-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - if (scripts[SE_MEROITIC]) { - addTrans("Meroitic-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_LINEARB]) { - addTrans("LinearB-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_CYPRIOT]) { - addTrans("Cypriot-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_RUNIC]) { - addTrans("Runic-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_OGHAM]) { - addTrans("Ogham-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_THAANA]) { - if (option == SE_ALALC) - addTrans("Thaana-Latin/ALALC", &ID); - else if (option == SE_BGNPCGN) - addTrans("Thaana-Latin/BGNPCGN", &ID); - else { - addTrans("Thaana-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - if (scripts[SE_GLAGOLITIC]) { - if (option == SE_ISO) - addTrans("Glagolitic-Latin/ISO", &ID); - else if (option == SE_ALALC) - addTrans("Glagolitic-Latin/ALALC", &ID); - else if (option == SE_ALALC) - addTrans("Glagolitic-Cyrillic", &ID); - else { - addTrans("Glagolitic-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - if (scripts[SE_THAI]) { - addTrans("Thai-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_THAI]) { - addTrans("Thai-Latin", &ID); - scripts[SE_LATIN] = true; - } - - if (scripts[SE_HAN]) { - if (!strnicmp (((SWModule*)module)->Lang(), "ja", 2)) { - addTrans("Kanji-Romaji", &ID); - } - else { - addTrans("Han-Latin", &ID); - } - scripts[SE_LATIN] = true; - } - - // Inter-Kana and Kana to Latin transliterators - if (option == SE_HIRAGANA && scripts[SE_KATAKANA]) { - addTrans("Katakana-Hiragana", &ID); - scripts[SE_HIRAGANA] = true; - } - else if (option == SE_KATAKANA && scripts[SE_HIRAGANA]) { - addTrans("Hiragana-Katakana", &ID); - scripts[SE_KATAKANA] = true; - } - else { - if (scripts[SE_KATAKANA]) { - addTrans("Katakana-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_HIRAGANA]) { - addTrans("Hiragana-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - - // Korean to Latin transliterators - if (scripts[SE_HANGUL]) { - addTrans("Hangul-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_JAMO]) { - addTrans("Jamo-Latin", &ID); - scripts[SE_LATIN] = true; - } - - // Indic-Latin - if (option < SE_DEVANAGARI || option > SE_MALAYALAM) { - // Indic to Latin - if (scripts[SE_TAMIL]) { - addTrans("Tamil-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_BENGALI]) { - addTrans("Bengali-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_GURMUKHI]) { - addTrans("Gurmukhi-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_GUJARATI]) { - addTrans("Gujarati-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_ORIYA]) { - addTrans("Oriya-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_TELUGU]) { - addTrans("Telugu-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_KANNADA]) { - addTrans("Kannada-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_MALAYALAM]) { - addTrans("Malayalam-Latin", &ID); - scripts[SE_LATIN] = true; - } - } - else { - if (scripts[SE_LATIN]) { - addTrans("Latin-InterIndic", &ID); - } - if (scripts[SE_DEVANAGARI]) { - addTrans("Devanagari-InterIndic", &ID); - } - if (scripts[SE_TAMIL]) { - addTrans("Tamil-InterIndic", &ID); - } - if (scripts[SE_BENGALI]) { - addTrans("Bengali-InterIndic", &ID); - } - if (scripts[SE_GURMUKHI]) { - addTrans("Gurmurkhi-InterIndic", &ID); - } - if (scripts[SE_GUJARATI]) { - addTrans("Gujarati-InterIndic", &ID); - } - if (scripts[SE_ORIYA]) { - addTrans("Oriya-InterIndic", &ID); - } - if (scripts[SE_TELUGU]) { - addTrans("Telugu-InterIndic", &ID); - } - if (scripts[SE_KANNADA]) { - addTrans("Kannada-InterIndic", &ID); - } - if (scripts[SE_MALAYALAM]) { - addTrans("Malayalam-InterIndic", &ID); - } - - switch(option) { - case SE_DEVANAGARI: - addTrans("InterIndic-Devanagari", &ID); - break; - case SE_TAMIL: - addTrans("InterIndic-Tamil", &ID); - break; - case SE_BENGALI: - addTrans("InterIndic-Bengali", &ID); - break; - case SE_GURMUKHI: - addTrans("InterIndic-Gurmukhi", &ID); - break; - case SE_GUJARATI: - addTrans("InterIndic-Gujarati", &ID); - break; - case SE_ORIYA: - addTrans("InterIndic-Oriya", &ID); - break; - case SE_TELUGU: - addTrans("InterIndic-Telugu", &ID); - break; - case SE_KANNADA: - addTrans("InterIndic-Kannada", &ID); - break; - case SE_MALAYALAM: - addTrans("InterIndic-Malayalam", &ID); - break; - default: - addTrans("InterIndic-Latin", &ID); - scripts[SE_LATIN] = true; - break; - } - } - - if (scripts[SE_TENGWAR]) { - addTrans("Tengwar-Latin", &ID); - scripts[SE_LATIN] = true; - } - if (scripts[SE_CIRTH]) { - addTrans("Cirth-Latin", &ID); - scripts[SE_LATIN] = true; - } - - if (scripts[SE_LATIN]) { - switch (option) { - case SE_GREEK: - addTrans("Latin-Greek", &ID); - break; - case SE_HEBREW: - addTrans("Latin-Hebrew", &ID); - break; - case SE_CYRILLIC: - addTrans("Latin-Cyrillic", &ID); - break; - case SE_ARABIC: - addTrans("Latin-Arabic", &ID); - break; - case SE_SYRIAC: - addTrans("Latin-Syriac", &ID); - break; - case SE_THAI: - addTrans("Latin-Thai", &ID); - break; - case SE_GEORGIAN: - addTrans("Latin-Georgian", &ID); - break; - case SE_ARMENIAN: - addTrans("Latin-Armenian", &ID); - break; - case SE_ETHIOPIC: - addTrans("Latin-Ethiopic", &ID); - break; - case SE_GOTHIC: - addTrans("Latin-Gothic", &ID); - break; - case SE_UGARITIC: - addTrans("Latin-Ugaritic", &ID); - break; - case SE_COPTIC: - addTrans("Latin-Coptic", &ID); - break; - case SE_KATAKANA: - addTrans("Latin-Katakana", &ID); - break; - case SE_HIRAGANA: - addTrans("Latin-Hiragana", &ID); - break; - case SE_JAMO: - addTrans("Latin-Jamo", &ID); - break; - case SE_HANGUL: - addTrans("Latin-Hangul", &ID); - break; - case SE_MEROITIC: - addTrans("Latin-Meroitic", &ID); - break; - case SE_LINEARB: - addTrans("Latin-LinearB", &ID); - break; - case SE_CYPRIOT: - addTrans("Latin-Cypriot", &ID); - break; - case SE_RUNIC: - addTrans("Latin-Runic", &ID); - break; - case SE_OGHAM: - addTrans("Latin-Ogham", &ID); - break; - case SE_THAANA: - addTrans("Latin-Thaana", &ID); - break; - case SE_GLAGOLITIC: - addTrans("Latin-Glagolitic", &ID); - break; - case SE_TENGWAR: - addTrans("Latin-Tengwar", &ID); - break; - case SE_CIRTH: - addTrans("Latin-Cirth", &ID); - break; - } - } - - if (option == SE_BASICLATIN) { - addTrans("Any-Latin1", &ID); - } - - addTrans("NFC", &ID); - - err = U_ZERO_ERROR; - Transliterator * trans = createTrans(UnicodeString(ID), UTRANS_FORWARD, err); - if (trans && !U_FAILURE(err)) { - UnicodeString target = UnicodeString(source); - trans->transliterate(target); - text.setSize(text.size()*2); - len = ucnv_fromUChars(conv, text.getRawData(), text.size(), target.getBuffer(), target.length(), &err); - text.setSize(len); - delete trans; - } - ucnv_close(conv); - } - return 0; -} - -SWORD_NAMESPACE_END -#endif - - - diff --git a/src/modules/filters/utf8utf16.cpp b/src/modules/filters/utf8utf16.cpp deleted file mode 100644 index 2fddf4c..0000000 --- a/src/modules/filters/utf8utf16.cpp +++ /dev/null @@ -1,78 +0,0 @@ -/****************************************************************************** - * - * UTF8UTF16 - SWFilter descendant to convert UTF-8 to UTF-16 - * - */ - -#include -#include - -#include - -SWORD_NAMESPACE_START - -UTF8UTF16::UTF8UTF16() { -} - - -char UTF8UTF16::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - const unsigned char *from; - - int len; - unsigned long uchar, uchars[10]; - unsigned char significantFirstBits, subsequent; - unsigned short schar; - - if ((unsigned long)key < 2) // hack, we're en(1)/de(0)ciphering - return -1; - - - SWBuf orig = text; - from = (const unsigned char *)orig.c_str(); - - for (text = ""; *from; from++) { - uchar = 0; - if ((*from & 128) != 128) { - //if (*from != ' ') - uchar = *from; - } - else if ((*from & 128) && ((*from & 64) != 64)) { - // error, do nothing - continue; - } - else { - uchars[0] = *from; - uchars[0] <<= 1; - for (subsequent = 1; (uchars[0] & 128) && (subsequent < 10); subsequent++) { - uchars[0] <<= 1; - uchars[subsequent] = from[subsequent]; - uchars[subsequent] &= 63; - uchar <<= 6; - uchar |= uchars[subsequent]; - } - subsequent--; - uchars[0] <<=1; - significantFirstBits = 8 - (2+subsequent); - - uchar |= (((short)uchars[0]) << (((6*subsequent)+significantFirstBits)-8)); - from += subsequent; - } - - if (uchar < 0x1ffff) { - text.setSize(text.size()+2); - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short)uchar; - } - else { - uchar -= 0x10000; - schar = 0xD800 | (uchar & 0x03ff); - uchar >>= 10; - uchar |= 0xDC00; - text.setSize(text.size()+4); - *((unsigned short *)(text.getRawData()+(text.size()-4))) = (unsigned short)schar; - *((unsigned short *)(text.getRawData()+(text.size()-2))) = (unsigned short)uchar; - } - } - return 0; -} - -SWORD_NAMESPACE_END -- cgit v1.2.3