void notes_handle_vcs_feedback (const ustring& directory, const ustring& feedback)
// This handles the feedback that comes from the version control system.
{
if (directory == notes_shared_storage_folder ()) {
unsigned int note_id = 0;
// The following feedback indicates that somebody created a new note:
// create mode 100644 27185458
if (feedback.find ("create mode") != string::npos) {
ustring s (feedback);
s.erase (12);
Parse parse (s);
if (parse.words.size () == 2) {
note_id = convert_to_int (parse.words[1]);
}
}
// The following feedback indicates that somebody modified a note:
// # modified: 27185458
if (feedback.find ("modified:") != string::npos) {
ustring s (feedback);
s.erase (12);
note_id = convert_to_int (number_in_string (feedback));
}
// The following feedback indicates that somebody deleted a note:
// # deleted: 46473236
if (feedback.find ("deleted:") != string::npos) {
ustring s (feedback);
s.erase (11);
note_id = convert_to_int (number_in_string (feedback));
}
// See the following:
// 95935882 | 9 +++++++++
// It means that this note was edited.
if (feedback.find (" | ") != string::npos) {
note_id = convert_to_int (number_in_string (feedback));
}
if (note_id != 0) {
gw_message (_("Change detected for note ") + convert_to_string (note_id));
// Update the index.
sqlite3 *db;
sqlite3_open(notes_index_filename ().c_str(), &db);
sqlite3_busy_timeout(db, 1000);
notes_store_index_entry (db, note_id);
sqlite3_close(db);
}
}
}
ustring resource_url_enter_reference(const ustring& constructor, map <unsigned int, ustring>& books, map <unsigned int, ustring>& books2, const Reference& reference)
{
ustring url (constructor);
replace_text(url, resource_url_constructor_book(), books[reference.book_get()]);
replace_text(url, resource_url_constructor_book2(), books2[reference.book_get()]);
replace_text(url, resource_url_constructor_chapter(), convert_to_string(reference.chapter_get()));
replace_text(url, resource_url_constructor_verse(), number_in_string(reference.verse_get()));
return url;
}
CategorizeChapterVerse::CategorizeChapterVerse(const vector < ustring > &lines)
// Categorizes the lines by adding chapter and verse information to it.
// It expects each \c and \v to start a new line, i.e. the lines are "clean".
// Gives one line per verse.
{
// Variables.
unsigned int chapternumber = 0;
ustring versenumber = "0";
ustring text;
unsigned int previous_chapter = 0;
ustring previous_verse = "0";
// Go through all the lines.
for (unsigned int i = 0; i < lines.size(); i++) {
// Extract the marker, and deal with it.
ustring ln = lines[i];
ustring marker = usfm_extract_marker(ln);
// Chapter.
if (marker == "c") {
ustring number_in_line = number_in_string(ln);
// Only accept the number if it is well-formed.
if ((ln.substr(0, number_in_line.length()) == number_in_line) && (!number_in_line.empty())) {
chapternumber = convert_to_int(number_in_line);
if (i == 0)
previous_chapter = chapternumber; // For one-chapter texts
versenumber = "0";
}
}
// Verse
if (marker == "v") {
versenumber = ln;
// Make it robust, even handling cases like:
// - \v 1-2"Moi - No space after verse number.
size_t spaceposition = versenumber.find_first_not_of("0123456789,-ab");
if (spaceposition != string::npos) {
versenumber = versenumber.substr(0, spaceposition);
}
// Handle case that the usfm file does not contain the \c 1.
if ((versenumber != "0") && (chapternumber == 0)) {
chapternumber = 1;
}
}
// Store data.
if ((chapternumber != previous_chapter) || (versenumber != previous_verse)) {
store(previous_chapter, previous_verse, text);
text.clear();
previous_chapter = chapternumber;
previous_verse = versenumber;
}
// Save text.
if (!text.empty())
text.append("\n");
text.append(lines[i]);
}
if (!text.empty())
store(chapternumber, versenumber, text);
}
void NotesTransferDialog::clean_note(ustring & note)
// "Cleans" the note: removes unnecessary stuff.
{
ustring working_copy(note);
ustring marker = usfm_extract_marker(working_copy);
if (marker == "v") {
usfm_extract_marker(note);
note = trim(note);
ustring verse = number_in_string(note);
note.erase(0, verse.length());
note = trim(note);
}
}
void GotoReferenceDialog::on_move_chapter()
{
extern Settings *settings;
// Chapter number changed, therefore update the verse numbers.
ustring chapter = listview_get_active_string(treeview_chapter);
// Something weird in Gtk: If the listview was not in view, it gives no results.
// Deal with that here.
if (chapter.empty())
return;
// Get the verses as they are in the chapter.
unsigned int bookid = books_name_to_id(language, listview_get_active_string(treeview_book));
vector < ustring > verses;
verses = project_get_verses(settings->genconfig.project_get(), bookid, convert_to_int(chapter));
// The verses may contain sequences and ranges, but fill them up with the
// verses contained in those. E.g.: 10-12 also contains 11.
vector < ustring > verses2;
set < ustring > verses2_set;
for (unsigned int i = 0; i < verses.size(); i++) {
verses2.push_back(verses[i]);
if (number_in_string(verses[i]) != verses[i]) {
vector < unsigned int >int_verses = verse_range_sequence(verses[i]);
for (unsigned int i2 = 0; i2 < int_verses.size(); i2++) {
ustring verse2 = convert_to_string(int_verses[i2]);
// No double verses will be listed.
if (verses2_set.find(verse2) == verses2_set.end()) {
verses2.push_back(verse2);
}
verses2_set.insert(verse2);
}
}
}
listview_set_strings(treeview_verse, store_verse, verses2);
if (oldbook == bookid)
if (oldchapter == convert_to_int(chapter))
listview_focus_string(treeview_verse, oldverse);
}
void CheckValidateUsfm::check(const ustring & text)
// Do the actual check of one verse.
{
// Extract the marker, and deal with it.
ustring utext = trim(text);
if (utext.empty())
return;
ustring line = utext;
ustring marker = usfm_extract_marker_within_line(line);
if (marker.empty()) {
// No marker found.
message(_("Line without USFM"));
}
while (!marker.empty()) {
if (marker == "id") {
// Is the line long enough?
if (line.length() < 3) {
message(_("ID line is too short: ") + line);
} else {
ustring id = line.substr(0, 3);
unsigned int myid = books_paratext_to_id(id);
if (myid == 0)
message(_("Unknown id ") + id);
if (id != upperCase(id))
message(_("Non-uppercase id code"));
}
} else if (marker == "c") {
} else if (marker == "v") {
// Is there a space after the verse number?
// Check it by extracting the text will the first space, and see if any unusual characters are in it.
// It should cover things like \v 10a-11b or \v 10,11
size_t position = line.find(" ");
position = CLAMP(position, 0, line.length());
ustring verse_number = line.substr (0, position);
for (unsigned int i = 0; i < verse_number.length(); i++) {
ustring character = verse_number.substr (i, 1);
if (number_in_string (character) != character) {
if ((character != "a") || (character != "b") || (character != "-") || (character != ",")) {
message (_("Unusual character in verse number ") + verse_number);
break;
}
}
}
} else if (marker == "add") {
check_on_endmarker(line, marker, false);
} else if (marker == "bdit") {
check_on_endmarker(line, marker, false);
deprecated_marker(marker);
} else if (marker == "bd") {
check_on_endmarker(line, marker, false);
deprecated_marker(marker);
} else if (marker == "bk") {
check_on_endmarker(line, marker, false);
} else if (marker == "b") {
} else if (marker == "ca") {
} else if (marker == "cd") {
} else if (marker == "cls") {
} else if (marker == "cl") {
} else if (marker == "conc") {
} else if (marker == "cov") {
} else if (marker == "cp") {
} else if (marker == "dc") {
check_on_endmarker(line, marker, false);
} else if (marker == "d") {
} else if (marker == "em") {
check_on_endmarker(line, marker, false);
deprecated_marker(marker);
} else if (marker == "fdc") {
check_on_endmarker(line, marker, true);
} else if (marker == "fe") {
check_on_endmarker(line, marker, false);
} else if (marker == "fig") {
check_on_endmarker(line, marker, false);
} else if (marker == "fk") {
check_on_endmarker(line, marker, true);
} else if (marker == "fl") {
check_on_endmarker(line, marker, true);
} else if (marker == "fm") {
check_on_endmarker(line, marker, false);
} else if (marker == "fp") {
} else if (marker == "fqa") {
check_on_endmarker(line, marker, true);
} else if (marker == "fq") {
check_on_endmarker(line, marker, true);
} else if (marker == "fr") {
check_on_endmarker(line, marker, true);
} else if (marker == "ft") {
check_on_endmarker(line, marker, true);
} else if (marker == "fv") {
check_on_endmarker(line, marker, true);
} else if (marker == "f") {
check_on_endmarker(line, marker, false);
} else if (marker == "fb") {
// todo rogue fix - this check needs to be based on stylesheet, not hard coded.
// A task was opened for this to be done.
check_on_endmarker(line, marker, false);
} else if (marker == "fx") {
// todo rogue fix - this check needs to be based on stylesheet, not hard coded.
// A task was opened for this to be done.
check_on_endmarker(line, marker, false);
} else if (marker == "glo") {
} else if (marker == "h1") {
} else if (marker == "h2") {
} else if (marker == "h3") {
} else if (marker == "h") {
} else if (marker == "ib") {
} else if (marker == "ide") {
} else if (marker == "idx") {
} else if (marker == "ie") {
} else if (marker == "iex") {
} else if (marker == "imi") {
} else if (marker == "imq") {
} else if (marker == "imt1") {
} else if (marker == "imt2") {
} else if (marker == "imt3") {
} else if (marker == "imt4") {
} else if (marker == "imte") {
} else if (marker == "imt") {
} else if (marker == "im") {
} else if (marker == "intro") {
} else if (marker == "io1") {
} else if (marker == "io2") {
} else if (marker == "io3") {
} else if (marker == "io4") {
} else if (marker == "ior") {
check_on_endmarker(line, marker, false);
} else if (marker == "iot") {
} else if (marker == "io") {
} else if (marker == "ipi") {
} else if (marker == "ipq") {
} else if (marker == "ipr") {
} else if (marker == "ip") {
} else if (marker == "iq1") {
} else if (marker == "iq2") {
} else if (marker == "iq3") {
} else if (marker == "iq") {
} else if (marker == "is1") {
} else if (marker == "is2") {
} else if (marker == "is") {
} else if (marker == "it") {
check_on_endmarker(line, marker, false);
deprecated_marker(marker);
} else if (marker == "k1") {
} else if (marker == "k2") {
} else if (marker == "k") {
check_on_endmarker(line, marker, false);
} else if (marker == "li1") {
} else if (marker == "li2") {
} else if (marker == "li3") {
} else if (marker == "li4") {
} else if (marker == "lit") {
} else if (marker == "li") {
} else if (marker == "maps") {
} else if (marker == "mi") {
} else if (marker == "mr") {
} else if (marker == "ms1") {
} else if (marker == "ms2") {
} else if (marker == "ms") {
} else if (marker == "mt1") {
} else if (marker == "mt2") {
} else if (marker == "mt3") {
} else if (marker == "mt4") {
} else if (marker == "mte1") {
} else if (marker == "mte2") {
} else if (marker == "mte") {
} else if (marker == "mt") {
} else if (marker == "m") {
} else if (marker == "nb") {
} else if (marker == "nd") {
check_on_endmarker(line, marker, false);
} else if (marker == "ndx") {
check_on_endmarker(line, marker, false);
} else if (marker == "no") {
check_on_endmarker(line, marker, false);
deprecated_marker(marker);
} else if (marker == "ord") {
check_on_endmarker(line, marker, false);
} else if (marker == "p1") {
} else if (marker == "p2") {
} else if (marker == "pb") {
} else if (marker == "pc") {
} else if (marker == "pi1") {
} else if (marker == "pi2") {
} else if (marker == "pi3") {
} else if (marker == "pi") {
} else if (marker == "pmc") {
} else if (marker == "pmo") {
} else if (marker == "pmr") {
} else if (marker == "pm") {
} else if (marker == "pn") {
check_on_endmarker(line, marker, false);
} else if (marker == "pref") {
} else if (marker == "pro") {
check_on_endmarker(line, marker, false);
} else if (marker == "pubinfo") {
} else if (marker == "pub") {
} else if (marker == "p") {
} else if (marker == "q1") {
} else if (marker == "q2") {
} else if (marker == "q3") {
} else if (marker == "qac") {
check_on_endmarker(line, marker, false);
} else if (marker == "qa") {
} else if (marker == "qc") {
} else if (marker == "qm1") {
} else if (marker == "qm2") {
} else if (marker == "qm3") {
} else if (marker == "qm") {
} else if (marker == "qr") {
} else if (marker == "qs") {
} else if (marker == "qt") {
check_on_endmarker(line, marker, false);
} else if (marker == "q") {
} else if (marker == "rem") {
} else if (marker == "restore") {
} else if (marker == "r") {
} else if (marker == "rq") {
} else if (marker == "s1") {
} else if (marker == "s2") {
} else if (marker == "s3") {
} else if (marker == "s4") {
} else if (marker == "sc") {
check_on_endmarker(line, marker, false);
deprecated_marker(marker);
} else if (marker == "sig") {
check_on_endmarker(line, marker, false);
} else if (marker == "sls") {
check_on_endmarker(line, marker, false);
} else if (marker == "spine") {
} else if (marker == "sp") {
} else if (marker == "sr") {
} else if (marker == "s") {
} else if (marker == "tc1") {
} else if (marker == "tc2") {
} else if (marker == "tc3") {
} else if (marker == "tc4") {
} else if (marker == "tcr1") {
} else if (marker == "tcr2") {
} else if (marker == "tcr3") {
} else if (marker == "tcr4") {
} else if (marker == "th1") {
} else if (marker == "th2") {
} else if (marker == "th3") {
} else if (marker == "th4") {
} else if (marker == "thr1") {
} else if (marker == "thr2") {
} else if (marker == "thr3") {
} else if (marker == "thr4") {
} else if (marker == "tl") {
check_on_endmarker(line, marker, false);
} else if (marker == "toc1") {
} else if (marker == "toc2") {
} else if (marker == "toc3") {
} else if (marker == "toc") {
} else if (marker == "tr") {
} else if (marker == "va") {
check_on_endmarker(line, marker, false);
} else if (marker == "vp") {
check_on_endmarker(line, marker, false);
} else if (marker == "wg") {
check_on_endmarker(line, marker, false);
} else if (marker == "wh") {
check_on_endmarker(line, marker, false);
} else if (marker == "wj") {
check_on_endmarker(line, marker, false);
} else if (marker == "w") {
check_on_endmarker(line, marker, false);
} else if (marker == "xdc") {
check_on_endmarker(line, marker, true);
} else if (marker == "xk") {
check_on_endmarker(line, marker, true);
} else if (marker == "xo") {
check_on_endmarker(line, marker, true);
} else if (marker == "xq") {
check_on_endmarker(line, marker, true);
} else if (marker == "xt") {
check_on_endmarker(line, marker, true);
} else if (marker == "x") {
check_on_endmarker(line, marker, false);
} else if (marker.find("*") != string::npos) {
message(_("Unmatched end marker ") + marker);
} else {
message(_("Unknown USFM ") + marker);
}
// Optionally check whether this marker is in the stylesheet.
if (mychecksheet) {
if (styles.find(marker) == styles.end()) {
message(_("Marker ") + marker + _(" not in stylesheet"));
}
}
// Extract any next marker in this line.
marker = usfm_extract_marker_within_line(line);
}
// Deal with accidentally entered forward slashes instead of backslashes.
line = utext;
marker = usfm_extract_marker_with_forwardslash(line);
while (!marker.empty()) {
ustring originalmarker(marker);
size_t pos = marker.find("*");
if (pos != string::npos) {
marker.erase(pos, 1);
}
if ((marker == "id")
|| (marker == "c")
|| (marker == "v")
|| (marker == "add")
|| (marker == "bdit")
|| (marker == "bd")
|| (marker == "bk")
|| (marker == "b")
|| (marker == "ca")
|| (marker == "cd")
|| (marker == "cls")
|| (marker == "cl")
|| (marker == "conc")
|| (marker == "cov")
|| (marker == "cp")
|| (marker == "dc")
|| (marker == "d")
|| (marker == "em")
|| (marker == "fdc")
|| (marker == "fe")
|| (marker == "fig")
|| (marker == "fk")
|| (marker == "fl")
|| (marker == "fm")
|| (marker == "fp")
|| (marker == "fqa")
|| (marker == "fq")
|| (marker == "fr")
|| (marker == "ft")
|| (marker == "fv")
|| (marker == "f")
|| (marker == "glo")
|| (marker == "h1")
|| (marker == "h2")
|| (marker == "h3")
|| (marker == "h")
|| (marker == "ib")
|| (marker == "ide")
|| (marker == "idx")
|| (marker == "ie")
|| (marker == "iex")
|| (marker == "imi")
|| (marker == "imq")
|| (marker == "imt1")
|| (marker == "imt2")
|| (marker == "imt3")
|| (marker == "imt4")
|| (marker == "imte")
|| (marker == "imt")
|| (marker == "im")
|| (marker == "intro")
|| (marker == "io1")
|| (marker == "io2")
|| (marker == "io3")
|| (marker == "io4")
|| (marker == "ior")
|| (marker == "iot")
|| (marker == "io")
|| (marker == "ipi")
|| (marker == "ipq")
|| (marker == "ipr")
|| (marker == "ip")
|| (marker == "iq1")
|| (marker == "iq2")
|| (marker == "iq3")
|| (marker == "iq")
|| (marker == "is1")
|| (marker == "is2")
|| (marker == "is")
|| (marker == "it")
|| (marker == "k1")
|| (marker == "k2")
|| (marker == "k")
|| (marker == "li1")
|| (marker == "li2")
|| (marker == "li3")
|| (marker == "li4")
|| (marker == "lit")
|| (marker == "li")
|| (marker == "maps")
|| (marker == "mi")
|| (marker == "mr")
|| (marker == "ms1")
|| (marker == "ms2")
|| (marker == "ms")
|| (marker == "mt1")
|| (marker == "mt2")
|| (marker == "mt3")
|| (marker == "mt4")
|| (marker == "mte1")
|| (marker == "mte2")
|| (marker == "mte")
|| (marker == "mt")
|| (marker == "m")
|| (marker == "nb")
|| (marker == "nd")
|| (marker == "ndx")
|| (marker == "no")
|| (marker == "ord")
|| (marker == "p1")
|| (marker == "p2")
|| (marker == "pb")
|| (marker == "pc")
|| (marker == "pi1")
|| (marker == "pi2")
|| (marker == "pi3")
|| (marker == "pi")
|| (marker == "pmc")
|| (marker == "pmo")
|| (marker == "pmr")
|| (marker == "pm")
|| (marker == "pn")
|| (marker == "pref")
|| (marker == "pro")
|| (marker == "pubinfo")
|| (marker == "pub")
|| (marker == "p")
|| (marker == "q1")
|| (marker == "q2")
|| (marker == "q3")
|| (marker == "qac")
|| (marker == "qa")
|| (marker == "qc")
|| (marker == "qm1")
|| (marker == "qm2")
|| (marker == "qm3")
|| (marker == "qm")
|| (marker == "qr")
|| (marker == "qs")
|| (marker == "qt")
|| (marker == "q")
|| (marker == "rem")
|| (marker == "restore")
|| (marker == "r")
|| (marker == "rq")
|| (marker == "s1")
|| (marker == "s2")
|| (marker == "s3")
|| (marker == "s4")
|| (marker == "sc")
|| (marker == "sig")
|| (marker == "sls")
|| (marker == "spine")
|| (marker == "sp")
|| (marker == "sr")
|| (marker == "s")
|| (marker == "tc1")
|| (marker == "tc2")
|| (marker == "tc3")
|| (marker == "tc4")
|| (marker == "tcr1")
|| (marker == "tcr2")
|| (marker == "tcr3")
|| (marker == "tcr4")
|| (marker == "th1")
|| (marker == "th2")
|| (marker == "th3")
|| (marker == "th4")
|| (marker == "thr1")
|| (marker == "thr2")
|| (marker == "thr3")
|| (marker == "thr4")
|| (marker == "tl")
|| (marker == "toc1")
|| (marker == "toc2")
|| (marker == "toc3")
|| (marker == "toc")
|| (marker == "tr")
|| (marker == "va")
|| (marker == "vp")
|| (marker == "wg")
|| (marker == "wh")
|| (marker == "wj")
|| (marker == "w")
|| (marker == "xdc")
|| (marker == "xk")
|| (marker == "xo")
|| (marker == "xq")
|| (marker == "xt")
|| (marker == "x")
) {
message(_("Normal slash for /") + originalmarker);
}
// Extract any next marker in this line.
marker = usfm_extract_marker_with_forwardslash(line);
}
// Check for widow backslashes.
line = utext + " ";
if ((line.find("\\ ") != string::npos) || (line == "\\")) {
message(_("Widow backslash"));
}
}
void PrintProject2::print()
// Runs the project through xetex and shows it in a pdf viewer.
{
// Scripture related data.
// Possible exclusion of books.
if (portionproject.empty())
portionproject = myproject->name;
scriptureportions = new ScripturePortions(portionproject);
if (scriptureportions->books.empty()) {
gtkw_dialog_info(NULL, _("There were no books to print\nSelect some books and try again"));
return;
}
// Create the XeTeX object.
XeTeX xetex (0);
// Usfm style object.
Usfm usfm (stylesheet_get_actual ());
// Collect usfm code for all the books.
for (unsigned int i = 0; i < scriptureportions->books.size(); i++) {
// Book id.
unsigned int book_id = books_english_to_id(scriptureportions->books[i]);
// Ranges to include.
WithinReferencesRange inrange;
{
vector <unsigned int> chapters_from, chapters_to;
vector <ustring> verses_from, verses_to;
select_portion_get_values(portionproject, book_id, scriptureportions->portions[i], chapters_from, verses_from, chapters_to, verses_to);
inrange.add_portion(book_id, chapters_from, verses_from, chapters_to, verses_to);
}
inrange.set_book (book_id);
inrange.set_chapter (0);
inrange.set_verse ("0");
// Open the book.
vector <ustring> full_book_lines;
for (unsigned int i2 = 0; i2 < myproject->data.size(); i2++) {
if (myproject->data[i2].number == book_id) {
full_book_lines = myproject->data[i2].get_data();
}
}
// Take only those portions the user wishes to print.
vector <ustring> book_lines;
for (unsigned int i = 0; i < full_book_lines.size(); i++) {
ustring line = full_book_lines[i];
ustring marker = usfm_extract_marker(line);
if (usfm.is_chapter_number(marker)) {
inrange.set_chapter (convert_to_int(number_in_string(line)));
inrange.set_verse ("0");
}
if (usfm.is_verse_number(marker)) {
size_t position = line.find(" ");
position = CLAMP(position, 0, line.length());
ustring verse = line.substr(0, position);
inrange.set_verse (verse);
}
if (inrange.in_range()) {
book_lines.push_back (full_book_lines[i]);
} else {
if (marker == "id") {
ParseLine parseline (full_book_lines[i]);
if (!parseline.lines.empty ()) {
book_lines.push_back (parseline.lines[0]);
}
}
}
}
// Do text replacements on the lines.
text_replacement(book_lines);
// Add the lines to the XeTeX object.
xetex.add_book (book_id, book_lines);
}
// Process the data.
ustring pdf_file = xetex.run ();
// Display the pdf file if there is one.
// There would be none if the formatting process was cancelled by the user.
if (!pdf_file.empty()) {
pdfviewer_view (pdf_file);
}
}
void import_bibleworks_text_file (const ustring& file, const ustring& bible, vector <ustring>& messages)
// Imports a bibleworks text file.
{
// Read the file.
ReadText rt (file, true, false);
// If there's nothing to import, bail out.
if (rt.lines.empty()) {
messages.push_back ("The file is empty");
}
// Divide the input into separate bits for each book.
vector <VectorUstring> bookdata;
if (messages.empty()) {
try {
ustring previousbook;
vector < ustring > booklines;
de_byte_order_mark (rt.lines[0]);
for (unsigned int i = 0; i < rt.lines.size(); i++) {
ustring currentbook = rt.lines[i].substr(0, 3);
if (i == 0) {
previousbook = currentbook;
}
if (currentbook != previousbook) {
bookdata.push_back (booklines);
booklines.clear();
previousbook = currentbook;
}
booklines.push_back(rt.lines[i]);
}
bookdata.push_back (booklines);
}
catch(exception & ex) {
messages.push_back(ex.what());
}
}
// Import each book.
if (messages.empty ()) {
ProgressWindow progresswindow ("Importing", false);
progresswindow.set_iterate (0, 1, bookdata.size());
for (unsigned int i = 0; i < bookdata.size(); i++) {
progresswindow.iterate ();
try {
// Input and output data.
vector <ustring> rawlines = bookdata[i];
vector <ustring> usfmlines;
// Get the name of the book.
unsigned int book_id = books_bibleworks_to_id(rawlines[0].substr(0, 3));
if (book_id == 0) {
messages.push_back ("Unknown book: " + rawlines[0]);
return;
}
// Store USFM id.
ustring usfmid = books_id_to_paratext (book_id);
usfmlines.push_back("\\id " + usfmid);
// Convert the BibleWorks lines to USFM code.
ustring previouschapter = "0";
for (unsigned int i = 0; i < rawlines.size(); i++) {
// Convert chapter information.
ustring line = rawlines[i];
line.erase(0, 4);
ustring currentchapter = number_in_string(line);
line.erase(0, currentchapter.length() + 1);
if (currentchapter != previouschapter) {
usfmlines.push_back("\\c " + currentchapter);
usfmlines.push_back("\\p");
previouschapter = currentchapter;
}
// Convert verse data.
usfmlines.push_back("\\v " + line);
}
// Store into the Bible.
CategorizeChapterVerse ccv(usfmlines);
project_store_book(bible, book_id, ccv);
}
catch(exception & ex) {
messages.push_back(ex.what());
}
}
}
}
vector <ustring> mechon_mamre_extract_contents (const ustring& file, unsigned int chapter)
{
// Usfm data.
vector <ustring> lines;
// Convert chapter number to USFM code.
lines.push_back("\\c " + convert_to_string(chapter));
lines.push_back("\\p");
// Read the text of the .htm file, and select only the .htm lines that
// contain the actual text.
vector < ustring > htmlines;
{
ReadText rt (file, true, false);
// Find lower boundary: the relevant parts start with a verse number.
unsigned int lower_boundary = 0;
for (unsigned int i = 0; i < rt.lines.size(); i++) {
if (rt.lines[i].find("A NAME=") != string::npos) {
lower_boundary = i;
break;
}
}
// Find higher boundary: the relevant part ends with a verse number
// that is one past the last verse.
unsigned int upper_boundary = 0;
for (unsigned int i = rt.lines.size() - 1; i > 0; i--) {
if (rt.lines[i].find("A NAME=") != string::npos) {
upper_boundary = i;
upper_boundary++;
break;
}
}
// Store the relevant html lines that contain the verses.
for (unsigned int i = lower_boundary; i <= upper_boundary; i++) {
htmlines.push_back(rt.lines[i]);
}
}
// Go through the relevant text and extract the verses.
ustring verse;
for (unsigned int ln = 0; ln < htmlines.size(); ln++) {
ustring s = number_in_string(htmlines[ln]);
if (!s.empty()) {
verse = "\\v " + s;
} else {
// A text line could be looking so (Psalms 1:1):
// <P><B>א</B> אַ֥שְֽׁרֵי הָאִ֗ישׁ אֲשֶׁ֤ר ׀ לֹ֥א הָלַךְ֮ בַּֽעֲצַ֪ת רְשָׁ֫עִ֥ים<BR>וּבְדֶ֣רֶךְ חַ֭טָּאִים לֹ֥א עָמָ֑ד וּבְמוֹשַׁ֥ב לֵ֝צִ֗ים לֹ֣א יָשָֽׁב׃<BR>
ustring line = htmlines[ln];
// Convert <BR>, </P>, etc.
replace_text(line, "<BR>", "\n\\nb\n");
replace_text(line, "</P>", "\n\\p\n");
replace_text(line, "<BIG>", "");
replace_text(line, "</BIG>", "");
replace_text(line, "{פ}", "");
replace_text(line, "{ס}", "");
size_t position = line.find_last_of(">");
line.erase(0, ++position);
line = trim(line);
lines.push_back(verse + " " + line);
}
}
// Return the data.
return lines;
}
void OpenDocument::format_general(vector <ustring>& lines)
// General formatter for USFM lines given.
{
// Go through all the lines.
odttextparagraph = NULL;
for (unsigned int ln = 0; ln < lines.size(); ln++) {
ustring line = lines[ln];
// Take any elastics out, put the \b marker instead.
replace_text(line, ELASTIC_MARKER, "b");
// Change certain characters to xml entities.
xml_handle_entities(line, NULL);
// Deal with footnotes.
odtfootnote->transform(line);
// Deal with endnotes.
odtendnote->transform(line);
// Deal with crossreferences.
odtxref->transform(line);
// Deal with inline text.
usfm_handle_inline_text(line, usfm_inline_markers, NULL, imOpenDocument, NULL);
// Signal new line.
if (odttextparagraph)
odttextparagraph->newline();
// Get the style belonging to the marker.
ustring marker = usfm_extract_marker(line);
if (usfm->is_identifier(marker)) {
// Handle some identifiers.
IdentifierType identifiertype = usfm->identifier_get_subtype(marker);
// New book.
if (identifiertype == itBook) {
if (odttextparagraph)
delete odttextparagraph;
odttextparagraph = new OdtTextParagraph(&odtlines, marker);
}
} else if (usfm->is_verse_number(marker)) {
// Because of dealing with portions to include/exclude, handle verse first.
// Get verse number. Handle combined verses too, e.g. 10-12b, etc.
size_t position = line.find(" ");
position = CLAMP(position, 0, line.length());
ustring versenumber = line.substr(0, position);
position++;
line.erase(0, position);
// There was a bug that the chapter number was missing from a book,
// and that results in text being inserted without the opening xml code.
// Solution: If no paragraph has been opened, open a default one.
if (odttextparagraph == NULL)
odttextparagraph = new OdtTextParagraph(&odtlines, "");
// Insert a bookmark at the verse.
// This will become an anchor for the Bibledit Resource Viewer,
// once OpenOffice saves the document to a HTML Document.
// Example bookmark: <text:bookmark text:name="Malachi_1_1"/>
ustring bookmark = resource_viewer_produce_anchor(anchor_book, anchor_chapter, convert_to_int(number_in_string(versenumber)));
bookmark.insert(0, "<text:bookmark text:name=\"");
bookmark.append("\"/>");
odttextparagraph->plaintext(bookmark);
// When the usfm is a verse number, then the number is put in the
// format specified by the stylesheet, but the remaining part of the
// line inherits the formatting from the paragraph it is in.
odttextparagraph->spannedtext(versenumber, marker);
odttextparagraph->plaintext(line);
} else if (usfm->is_starting_paragraph(marker)) {
if (odttextparagraph)
delete odttextparagraph;
odttextparagraph = new OdtTextParagraph(&odtlines, marker);
if (!line.empty())
odttextparagraph->plaintext(line);
} else if (usfm->is_inline_text(marker)) {
// Inline text, has been dealt with before (therefore should never occur here).
if (odttextparagraph)
odttextparagraph->spannedtext(line, marker);
} else if (usfm->is_chapter_number(marker)) {
// Close possible open paragraph.
if (odttextparagraph)
delete odttextparagraph;
// Signal new chapter to footnotes object.
odtfootnote->new_chapter();
// Store chapter for the anchors.
anchor_chapter = convert_to_int(number_in_string(line));
// Insert or prepare chapter text.
odttextparagraph = new OdtTextParagraph(&odtlines, marker);
odttextparagraph->plaintext(line);
} else if (usfm->is_peripheral(marker)) {
} else if (usfm->is_picture(marker)) {
} else if (usfm->is_pagebreak(marker)) {
if (odttextparagraph)
delete odttextparagraph;
odttextparagraph = new OdtTextParagraph(&odtlines, marker);
} else {
// Fallback for unknown marker or no marker.
if (!odttextparagraph)
odttextparagraph = new OdtTextParagraph(&odtlines, "");
odttextparagraph->plaintext(line);
// Make a note of this marker, that it was not formatted.
unformatted_markers.insert (marker);
}
}
// Close possible last paragraph.
if (odttextparagraph)
delete odttextparagraph;
}
// Returns an array with the verse numbers found in $usfm.
// It handles a single verse, a range of verses, or a sequence of verses.
// It locates separate whole verse numbers.
// Examples:
// 10
// 10-12b
// 10,11a
// 10,12
vector <int> usfm_get_verse_numbers (string usfm)
{
vector <int> verse_numbers = { 0 };
vector <string> markers_and_text = usfm_get_markers_and_text (usfm);
bool extract_verse = false;
for (string marker_or_text : markers_and_text) {
if (extract_verse) {
string verse = usfm_peek_verse_number (marker_or_text);
// If there is a range, take the beginning and the end and fill up in between.
if (verse.find("-") != string::npos) {
size_t position;
position = verse.find("-");
string start_range, end_range;
start_range = verse.substr (0, position);
verse.erase (0, ++position);
end_range = verse;
unsigned int start_verse_i = convert_to_int(number_in_string(start_range));
unsigned int end_verse_i = convert_to_int(number_in_string(end_range));
for (unsigned int i = start_verse_i; i <= end_verse_i; i++) {
if (i == start_verse_i)
verse_numbers.push_back (convert_to_int (start_range));
else if (i == end_verse_i)
verse_numbers.push_back (convert_to_int (end_range));
else
verse_numbers.push_back (i);
}
}
// Else if there is a sequence, take each verse in the sequence, and store it.
else if (verse.find(",") != string::npos) {
int iterations = 0;
do {
// In case of an unusual range formation, do not hang, but give message.
iterations++;
if (iterations > 50) {
break;
}
size_t position = verse.find (",");
string vs;
if (position == string::npos) {
vs = verse;
verse.clear ();
} else {
vs = verse.substr (0, position);
verse.erase(0, ++position);
}
verse_numbers.push_back (convert_to_int (vs));
} while (!verse.empty());
}
// No range and no sequence: a single verse.
else {
verse_numbers.push_back (convert_to_int (verse));
}
extract_verse = false;
}
if (marker_or_text.substr (0, 2) == "\\v") {
extract_verse = true;
}
}
return verse_numbers;
}
void CheckChaptersVerses::verses_check(unsigned int book, unsigned int chapter, const vector < ustring > &verses)
// This checks all the verses that are in 'book' and 'chapter'.
// It supports sequences in the form of \v 1,2,3,
// and ranges in the form of \v 1b-3 and \v 2-4a and \v 2b-5a.
{
// Check whether there are any verses at all. If not, stop further
// processing because the following code assumes there are verses.
if (verses.empty()) {
message(book, chapter, "1", _("Chapter has no verses"));
return;
}
// Check for verses in chapter 0, which indicates the \c 1 marker wasn't there.
if ((chapter == 0) && (verses.size() > 1)) {
message(book, chapter, "1", _("Chapter marker missing"));
}
// Transform the verses in the internally used encoding, so as to accomodate
// for sequences and ranges.
vector < unsigned int >expanded_verses;
vector < unsigned int >verses_pointers;
for (unsigned int i = 0; i < verses.size(); i++) {
// Do not work in the container, but on a copy.
ustring vs(verses[i]);
// If there is a range, take the beginning and the end and fill up in between.
if (vs.find("-") != string::npos) {
size_t position;
position = vs.find("-");
ustring start_range, end_range;
start_range = vs.substr(0, position);
vs.erase(0, ++position);
end_range = vs;
int start_expanded_verse = 2 * convert_to_int(number_in_string(start_range));
if (start_range.find("b") != string::npos)
start_expanded_verse++;
// Checking on range start.
if (start_range.find("a") != string::npos)
message(book, chapter, verses[i], _("Range starts with \"a\""));
int end_expanded_verse = 2 * convert_to_int(number_in_string(end_range));
if (end_range.find("a") == string::npos)
end_expanded_verse++;
// Check on range end.
if (end_range.find("b") != string::npos)
message(book, chapter, verses[i], _("Range ends with \"b\""));
for (int i2 = start_expanded_verse; i2 <= end_expanded_verse; i2++) {
expanded_verses.push_back(i2);
verses_pointers.push_back(i);
}
}
// If there is a sequence, take each verse in the sequence, and store it.
else if (vs.find(",") != string::npos) {
int iterations = 0;
do {
// In case of an unusual range formation, do not hang, but give message.
iterations++;
if (iterations > 50) {
message(book, chapter, verses[i], _("Unusual verse sequence"));
break;
}
size_t position = vs.find(",");
ustring verse;
if (position == string::npos) {
verse = vs;
vs.clear();
} else {
verse = vs.substr(0, position);
vs.erase(0, ++position);
}
store_expanded_verse(verse, i, expanded_verses, verses_pointers);
} while (!vs.empty());
}
// No range and no sequence: a "normal" verse.
else {
store_expanded_verse(vs, i, expanded_verses, verses_pointers);
}
}
// See whether it starts at verse 0 or 1.
if (expanded_verses[0] > 2)
message(book, chapter, verses[0], "Verse 1 missing");
// See whether the verses are within the limit.
for (unsigned int i = 0; i < expanded_verses.size(); i += 2) {
unsigned int verse;
verse = expanded_verses[i] / 2;
if (verse > highest_verse) {
message(book, chapter, convert_to_string(verse), _("Extra verse or wrong versification"));
}
}
// See whether there are verses or bits out of sequence.
int previous_verse = expanded_verses[0] - 1;
for (unsigned int i = 0; i < expanded_verses.size(); i++) {
ustring previous_verse_text;
unsigned int pointer = verses_pointers[i];
if (pointer == 0)
previous_verse_text = _("beginning");
else
previous_verse_text = verses[pointer - 1];
if ((int)expanded_verses[i] != previous_verse + 1) {
message(book, chapter, verses[pointer], _("Verse out of sequence following ") + previous_verse_text);
}
previous_verse = expanded_verses[i];
}
// Check whether we have enough verses.
int highverse = expanded_verses[expanded_verses.size() - 1];
highverse = highverse / 2;
if (highverse < (int)highest_verse) {
message(book, chapter, verses[verses.size() - 1], _("Not enough verses in chapter"));
}
// Clear storage.
expanded_verses.clear();
verses_pointers.clear();
}
// Import raw $text into $bible $book $chapter.
void bible_import_text (string text, string bible, int book, int chapter)
{
// Consecutive discoveries.
bool discoveries_passed = true;
// Split the input text into separate lines.
vector <string> lines = filter_string_explode (text, '\n');
// Go through the lines.
for (size_t i = 0; i < lines.size(); i++) {
// Trim the line.
lines[i] = filter_string_trim (lines[i]);
// Skip empty line.
if (lines[i].empty())
continue;
// Remove chapter markup.
if (lines[i].find("\\c") != string::npos) {
lines[i].clear();
continue;
}
// Skip line starting with a backslash. The rationale is that this line already has markup.
if (lines[i].substr(0, 1) == "\\")
continue;
// If the line is a number on its own, and the number agrees with the chapter number
// that was set, it silently removes this line. But if it differs, an error comes up.
if (discoveries_passed) {
if (number_in_string(lines[i]) == lines[i]) {
int number = convert_to_int (number_in_string (lines[i]));
if (number == chapter) {
lines[i].clear();
continue;
}
string msg = "The line that contains " + lines[i] + " looks like a chapter number, but the number differs from the chapter that was set";
Database_Logs::log (msg);
discoveries_passed = false;
}
}
// If the line has no number in it,
// and it ends with some type of punctuation,
// it is considered a a normal paragraph.
// If no punctuation at the end, it is a section heading.
if (discoveries_passed) {
if (number_in_string(lines[i]).empty()) {
string last_character = lines[i].substr(lines[i].length() -1, 1);
if (unicode_string_is_punctuation (last_character)) {
lines[i].insert(0, "\\p ");
} else {
lines[i].insert(0, "\\s ");
}
continue;
}
}
// If a number is found in the line, then this is considered a verse number.
// The first time a number is found, a \p is prefixed.
bool paragraph_open = false;
if (discoveries_passed) {
string output;
string number = number_in_string(lines[i]);
// Setting for having the number only at the start of the line.
bool treat_as_normal_paragraph = false;
bool verses_at_start = true;
if (verses_at_start) {
if (lines[i].find (number) != 0) {
number.clear();
treat_as_normal_paragraph = true;
}
}
if (treat_as_normal_paragraph) {
// Normal paragraph.
lines[i].insert(0, "\\p ");
} else {
// Find all verse numbers.
while (!number.empty()) {
if (!paragraph_open) {
output.append("\\p");
paragraph_open = true;
}
size_t pos = lines[i].find(number);
if (pos > 0) {
output.append(" " + lines[i].substr(0, pos));
lines[i].erase(0, pos);
}
output.append ("\n\\v ");
output.append (number);
output.append (" ");
lines[i].erase (0, number.length());
lines[i] = filter_string_trim (lines[i]);
number = number_in_string(lines[i]);
// Setting for discovering only first number in a paragraph.
if (verses_at_start) {
number.clear();
}
}
}
// Store line.
output.append(lines[i]);
lines[i] = output;
}
}
// Make one block of text.
string newtext;
for (unsigned int i = 0; i < lines.size(); i++) {
if (lines[i].empty())
continue;
filter_string_str_replace (" ", " ", lines[i]);
filter_string_str_replace (" \n", "\n", lines[i]);
newtext.append(lines[i]);
newtext.append("\n");
}
// If no chapter marker is found, insert it at the top.
if (newtext.find("\\c") == string::npos) {
newtext.insert(0, "\\c " + convert_to_string(chapter) + "\n");
}
// Import the text as USFM.
bible_logic_store_chapter (bible, book, chapter, newtext);
string book_name = Database_Books::getUsfmFromId (book);
Database_Logs::log ("Imported " + book_name + " " + convert_to_string (chapter) + ": " + text);
}
void CheckValidateReferences::check(const ustring & text)
// Do the actual check of one verse.
{
// Bail out if the verse is empty.
if (text.empty())
return;
// Extract the references and check them all.
ReferencesScanner refscanner(language, book, text);
for (unsigned int i = 0; i < references.size(); i++) {
// Check whether the reference fits within the limits of the versification system.
bool reference_fits = true;
unsigned int highest_chapter = 0;
vector < unsigned int >chapters = versification_get_chapters(versification, refscanner.references[i].book_get());
if (!chapters.empty())
highest_chapter = chapters[chapters.size() - 1];
if (refscanner.references[i].chapter_get() > highest_chapter)
reference_fits = false;
unsigned int last_verse = convert_to_int(versification_get_last_verse(versification,
refscanner.references[i].book_get(),
refscanner.references[i].chapter_get()));
unsigned int this_verse = convert_to_int(refscanner.references[i].verse_get());
if (this_verse > last_verse)
reference_fits = false;
if (!reference_fits) {
message(refscanner.references[i].human_readable(language) + _(" does not fit in the versification system"));
}
// Check whether the reference exists in the project.
if (reference_fits) {
ustring versetext = project_retrieve_verse(myproject, refscanner.references[i]);
if (versetext.empty()) {
message(refscanner.references[i].human_readable(language) + _(" contains no text"));
}
}
}
// Look for chapter/verse pairs by pattern, and check on these.
ustring mytext(text);
while (mytext.length() > 5) {
if (text_starts_chapter_verse(mytext)) {
// This text starts a chapter/verse string.
// Look for the dot or colon.
size_t position = mytext.find_first_of(".:");
if (position != string::npos) {
unsigned int mychapter = convert_to_int(mytext.substr(0, position));
mytext.erase(0, ++position);
ustring myverse = number_in_string(mytext);
mytext.erase(0, myverse.length());
bool referencefound = false;
for (unsigned int i = 0; i < references.size(); i++) {
if (refscanner.references[i].chapter_get() == mychapter)
if (refscanner.references[i].verse_get() == myverse)
referencefound = true;
}
if (!referencefound) {
message(_("Unrecognized chapter ") + convert_to_string(mychapter) + _(" and verse ") + myverse);
}
}
mytext.erase(0, 3);
} else {
// No chapter/verse string: erase one character and try again.
mytext.erase(0, 1);
}
}
}