summaryrefslogtreecommitdiffstats
path: root/migratetags/migratetags.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'migratetags/migratetags.cpp')
-rw-r--r--migratetags/migratetags.cpp73
1 files changed, 49 insertions, 24 deletions
diff --git a/migratetags/migratetags.cpp b/migratetags/migratetags.cpp
index 2051a22..689640a 100644
--- a/migratetags/migratetags.cpp
+++ b/migratetags/migratetags.cpp
@@ -50,7 +50,7 @@ void usage(const char *progName, const char *error = 0) {
int main(int argc, char **argv) {
const char *progName = argv[0];
- for (int i = 1; i < argc; i++) {
+ for (int i = 1; i < argc; ++i) {
if (!strcmp(argv[i], "-v")) {
optionDebug = true;
}
@@ -62,7 +62,7 @@ int main(int argc, char **argv) {
}
else usage(progName, (((SWBuf)"Unknown argument: ")+ argv[i]).c_str());
}
- VerseKey vk;
+
SWMgr lib;
lib.setGlobalOption("Textual Variants", "Secondary Reading");
SWModule *m = lib.getModule(targetModuleName);
@@ -246,15 +246,40 @@ if (optionDebug) {
cout << "\nTargetMod Words: " << endl;
}
bool warned = false;
- for (int i = 0; i < targetWords.size(); i++) {
+ for (int i = 0; i < targetWords.size(); ++i) {
if (targetWordTags[i] == -1 && !strstr(ignoreSeries, targetWords[i])) {
- if (!warned) cerr << "*** Error: didn't match all words: " << targetMod.getKeyText() << endl;
- warned = true;
+ if (!warned) {
+ cerr << "*** Error: didn't match all words: " << targetMod.getKeyText() << endl;
+ cerr << strongsSourceModuleName << ":";
+ for (int j = 0; j < fromWords.size(); ++j) {
+ cerr << " " << fromWords[j];
+ }
+ cerr << endl;
+ cerr << targetModuleName << ":";
+ for (int j = 0; j < targetWords.size(); ++j) {
+ cerr << " " << targetWords[j];
+ }
+ cerr << endl;
+ cerr << endl;
+ cerr << "Unmatched Words:" << endl;
+ warned = true;
+ }
+ cerr << " " << i << ": " << targetWords[i] << " (" << matcher->sanitizeWord(targetWords[i]) << ")" << endl;
}
if (optionDebug) {
cout << targetWords[i] << " : " << targetWordTags[i] << " => " << (targetWordTags[i] != -1 ? wordTags[targetWordTags[i]] : "") << endl;
}
}
+ if (warned) {
+ cerr << "\n" << targetModuleName << " Tags:\n";
+ VerseKey *vk = (VerseKey *)targetMod.getKey();
+ for (int j = 0; j < targetWords.size(); ++j) {
+ if (!strstr(ignoreSeries, targetWords[j])) {
+ cerr << targetWords[j] << "\t\t " << vk->getOSISRef() << "." << j << "=" << (targetWordTags[j] != -1 ? wordTags[targetWordTags[j]] : "") << endl;
+ }
+ }
+ cerr << "---------------------" << endl;
+ }
if (optionDebug) {
cout << "---------------------" << endl;
@@ -279,7 +304,7 @@ SWBuf findCanonicalBibleText(SWBuf orig, BibMap &bibMap, BibMap &wTags) {
int tagLevel = 0;
int wTag = -1;
int inTag = 0;
- for (int i = 0; i < orig.length(); i++) {
+ for (int i = 0; i < orig.length(); ++i) {
if (orig[i] == '<') {
inTag = true;
}
@@ -330,7 +355,7 @@ void insert(SWBuf addText, SWBuf &out, int bibPos, BibMap &bibMap, BibMap &wTags
}
if (!after || wTags[bibPos] == -1) {
out.insert(to, addText);
- for (int i = bibPos+((after)?1:0); i < bibMap.size(); i++) {
+ for (int i = bibPos+((after)?1:0); i < bibMap.size(); ++i) {
bibMap[i] += addText.length();
if (wTags[i] != -1) wTags[i] += addText.length();
}
@@ -338,7 +363,6 @@ void insert(SWBuf addText, SWBuf &out, int bibPos, BibMap &bibMap, BibMap &wTags
}
-
SWBuf buildWordMaps(const SWBuf &markupBuf, const BibMap &bibMap, vector<SWBuf> &targetWords, vector<int> &targetWordStarts, vector<int> &targetWordEnds) {
SWBuf bibWord = "";
SWBuf fromWord = "";
@@ -386,36 +410,38 @@ void pullFromModData(SWModule &fromMod, vector<XMLTag>&wordTags, vector<SWBuf> &
// this is our new <w> XMLTag.
// attributes will be added below
XMLTag w("w");
+ // this only gives us word count, not if we have multiple entries per word
+ // don't use as loop
int parts = atoi(it->second["PartCount"]);
SWBuf lemma = "";
SWBuf morph = "";
- for (int i = 1; i <= parts; i++) {
+ bool found = true;
+ for (int i = 1; found; ++i) {
+ found = false;
SWBuf key = "";
- key = (parts == 1) ? "Lemma" : SWBuf().setFormatted("Lemma.%d", i);
+ key = SWBuf().setFormatted("Lemma.%d", i);
AttributeValue::iterator li = it->second.find(key);
+ if (i == 1 && li == it->second.end()) li = it->second.find("Lemma");
if (li != it->second.end()) {
+ found = true;
if (i > 1) lemma += " ";
- key = (parts == 1) ? "LemmaClass" : SWBuf().setFormatted("LemmaClass.%d", i);
+ key = SWBuf().setFormatted("LemmaClass.%d", i);
AttributeValue::iterator lci = it->second.find(key);
+ if (i == 1 && lci == it->second.end()) lci = it->second.find("LemmaClass");
if (lci != it->second.end()) {
lemma += lci->second + ":";
}
lemma += li->second;
}
- key = (parts == 1) ? "Morph" : SWBuf().setFormatted("Morph.%d", i);
+ key = SWBuf().setFormatted("Morph.%d", i);
li = it->second.find(key);
- // silly. sometimes morph counts don't equal lemma counts
- if (i == 1 && parts != 1 && li == it->second.end()) {
- li = it->second.find("Morph");
- }
+ if (i == 1 && li == it->second.end()) li = it->second.find("Morph");
if (li != it->second.end()) {
+ found = true;
if (i > 1) morph += " ";
- key = (parts == 1) ? "MorphClass" : SWBuf().setFormatted("MorphClass.%d", i);
+ key = SWBuf().setFormatted("MorphClass.%d", i);
AttributeValue::iterator lci = it->second.find(key);
- // silly. sometimes morph counts don't equal lemma counts
- if (i == 1 && parts != 1 && lci == it->second.end()) {
- lci = it->second.find("MorphClass");
- }
+ if (i == 1 && lci == it->second.end()) lci = it->second.find("MorphClass");
if (lci != it->second.end()) {
morph += lci->second + ":";
}
@@ -430,9 +456,8 @@ void pullFromModData(SWModule &fromMod, vector<XMLTag>&wordTags, vector<SWBuf> &
fromWord = it->second["Text"];
bibWord = "";
- for (int j = 0; j < fromWord.length(); j++) {
+ for (int j = 0; j < fromWord.length(); ++j) {
char c = fromWord[j];
-// if (!strchr(ignoreSeries, c)) {
if (c != ' ' && c != '.' && c != ';' && c != ',') {
bibWord += c;
}
@@ -458,7 +483,7 @@ void insertWordTags(SWBuf &markupBuf, BibMap &bibMap, BibMap &wTags, const vecto
// TODO: this method needs some work,
// like putting multiple consecutive words
// together in one tag
- for (int i = 0; i < targetWordTags.size(); i++) {
+ for (int i = 0; i < targetWordTags.size(); ++i) {
if (targetWordTags[i] > -1) {
insert((const char *)wordTags[targetWordTags[i]], markupBuf, targetWordStarts[i], bibMap, wTags);
insert("</w>", markupBuf, targetWordEnds[i], bibMap, wTags, true);
generated by cgit (git 2.34.1) at 2024-09-19 01:29:10 +0000