scripture-guide 1.0.80 → 1.0.82
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/scriptures.cjs +54 -21
- package/dist/scriptures.mjs +54 -21
- package/package.json +4 -1
package/dist/scriptures.cjs
CHANGED
|
@@ -167,8 +167,8 @@ const raw_regex_orig = {
|
|
|
167
167
|
["([0-9]),*\\s*\\b(?:chapt*ers*|ch|chptrs*)\\.*,*\\s*([0-9])", "$1:$2"],
|
|
168
168
|
["([a-z]),*\\s*\\b(?:chapt*ers*|ch|chptrs*)\\s*([0-9])", "$1 $2"],
|
|
169
169
|
["[()]+", " "],
|
|
170
|
+
["(?:&(?:ndash|mdash|minus)|&#(?:8211|8212|8722))", "-"],
|
|
170
171
|
["[\\s.]*[–—−\\-]+[\\s.]*", "-"],
|
|
171
|
-
["–", "-"],
|
|
172
172
|
["([;,])\\s*and\\s*", "$1"],
|
|
173
173
|
["([0-9])[ .]*and[ .]*", "$1,"],
|
|
174
174
|
["(\\d)(\\.|: )(\\d)", "$1:$3"],
|
|
@@ -289,8 +289,8 @@ const raw_lang = {
|
|
|
289
289
|
[";\\s*Giao", "và Giao"],
|
|
290
290
|
],
|
|
291
291
|
books:{
|
|
292
|
-
"Sáng Thế": ["STK[yý]", "Sáng Thế Ký","S[áa]ng *Th[ếe] *(K[yý])*"], "Xuất Ê Díp Tô": ["X[ÊE]DT(K[ýy])*","X[úu]at *Ê *D[íi]p *T[ôo] *(K[yý])*","Xu[ấa]t h[àa]nh *(k[yý])*"], "Lê Vi": ["L[êe] *Vi *(K[yý])*","LV(K[ýy])*"], "Dân Số": ["DS(K[yý])*","D[âa]n *S[ốo] *(K[yý])*"], "Phục Truyền Luật Lệ": ["PTLL(K[yý])*","Ph[úu]c *Truy[ềe]n *Lu[ậa]t *L[ệe] *(K[yý])*"], "Giô Suê": ["Gi[ôo] *Su[êe]"], "Các Quan Xét": ["C[áa]c *Quan *X[ée]t","QX[ée]t"], "Ru Tơ": ["Ru *T[ơo]"], "1 Sa Mu Ên": ["1 *Sa *Mu *Ên","1 *SM[EÊ]n"], "2 Sa Mu Ên": ["2 *Sa *Mu *Ên","2 *SM[EÊ]n"], "1 Các Vua": ["1 *C[áa]c *Vua","1 *Vua"], "2 Các Vua": ["2 *C[áa]c *Vua","2 *Vua"], "1 Sử Ký": ["1 *S[ửu] *K[yý]"], "2 Sử Ký": ["2 *S[ửu] *K[yý]"], "E Xơ Ra": ["E *X[ơo] *Ra"], "Nê Hê Mi": ["N[êe] *H[êe] *Mi"], "Ê Xơ Tê": ["Ê *X[ơo] *T[êe]"], "Gióp": ["Gi[óo]p"], "Thi Thiên": ["Th*i* *Thi[êe]n"], "Châm Ngôn": ["Ch[âa]m *Ng[ôo]n","CNg[ôo]n"], "Truyền Đạo": ["T[DĐ][aạ]o","Truy[ềe]n *[ĐD]a[ọo]"], "Nhã Ca": ["Nh[ãa] *Ca"], "Ê Sai": ["[ÊE] *Sai"], "Giê Rê Mi": ["GRMi","Gi[êe] *R[êe] *Mi"], "Ca Thương": ["CTh[uư][oơ]ng","Ca *Th[ưu]ng"], "Ê Xê Chi Ên": ["[EÊ]XC[EÊ]n","Ê *X[êe] *Chi *[ÊE]n"], "Đa Ni Ên": ["[DĐ]N[EÊ]n","[ĐD]a *Ni *[ÊE]n"], "Ô Sê": ["[ÔO] *S[êe]"], "Giô Ên": ["Gi[ôo] *[ÊE]n"], "A Mốt": ["A *M[ốo]t"], "Áp Đia": ["[ÁA]p *Đia"], "Giô Na": ["Gi[ôo] *Na"], "Mi Chê": ["Mi *Ch[êe]"], "Na Hum": ["Na *Hum"], "Ha Ba Cúc": ["HBCuc","Ha *Ba *C[úu]c"], "Sô Phô Ni": ["S[ôo]* *Ph*[ôo]* *Ni"], "A Ghê": ["A *Gh[êe]"], "Xa Cha Ri": ["Xa* *Ch*a* *Ri"], "Ma La Chi": ["Ma* *La* *Chi"],
|
|
293
|
-
"Ma Thi Ơ": ["Ma *Thi *[ƠO]","MT[OƠ]"], "Mác": ["M[áa]c"], "Lu Ca": ["Lu *Ca"], "Giăng": ["Gio*[ăa]ng*"], "Công Vụ Các Sứ Đồ": ["C[ôo]ng *Vụ *C[áa]c *Sứ *Đ[ồo]", "CVCS[ĐD]"], "Rô Ma": ["R[ôo] *Ma"], "1 Cô Rinh Tô": ["1 *C[ôo]* *Ri*n*h* *T[ôo]"], "2 Cô Rinh Tô": ["2 *C[ôo]* *Ri*n*h* *T[ôo]"], "Ga La Ti": ["Ga *La *Ti"], "Ê Phê Sô": ["[ÊE] *Ph[êe] *S[ôo]","[ÊE]PS[ÔO]"], "Phi Líp": ["Phi *L[íi]p"], "Cô Lô Se": ["C[ôo] *L[ôo] *Se","CL[ÔO]*Se"], "1 Tê Sa Lô Ni Ca": ["1 *Tê *Sa *L[ôo] *Ni *Ca","1 *TSLN[ÔO]Ca","1 TSLNCa"], "2 Tê Sa Lô Ni Ca": ["2 TSLNCa","2 *Tê *Sa *L[ôo] *Ni *Ca","2 *TSLN[ÔO]Ca"], "1 Ti Mô Thê": ["1 *Ti *Mô *Th[êe]","1 *TMTh[ÊE]"], "2 Ti Mô Thê": ["2 *Ti *Mô *Th[êe]","2 *TMTh[ÊE]"], "Tít": ["T[íi]t"], "Phi Lê Môn": ["Phi *L[êe] *Môn","PL[ÊE]M[ÔO]n","PLM[oô]n"], "Hê Bơ Rơ": ["H[êe] *Bơ *Rơ","HBR[ƠO]"], "Gia Cơ": ["GLTi", "Gia *C[ơo]"], "1 Phi E Rơ": ["1 *Phi *E *R[ơo]","1 *PER[ƠO]"], "2 Phi E Rơ": ["2 *Phi *E *R[ơo]","2 *PER[ƠO]"], "1 Giăng": ["1 *Gio*[ăa]ng*"], "2 Giăng": ["2 *Gio*[ăa]ng*"], "3 Giăng": ["3 *Gio*[ăa]ng*"], "Giu Đe": ["Giu *[ĐD]e"], "Khải Huyền": ["Kh[ảa]i *Huy[ềe]n","KHuy[ềe]n"], "1 Nê Phi": ["1 *N[êe] *Phi"], "2 Nê Phi": ["2 *N[êe] *Phi"], "Gia Cốp": ["Gi*a* *C[ốo]p"], "Ê Nót": ["[ÊE] *N[óo]t"], "Gia Rôm": ["Gi*a* *R[ôo]m"], "Ôm Ni": ["[ÔO]m *Ni"], "Lời Mặc Môn": ["L[ờo]i *M[ặa]c *M[ôo]n","LMM[ÔO]n"], "Mô Si A": ["M[ôo] *Si *A"], "An Ma": ["An *Ma"], "Hê La Man": ["H[êe]* *La* *Man"], "3 Nê Phi": ["3 *N[êe] *Phi"], "4 Nê Phi": ["4 *N[êe] *Phi"], "Mặc Môn": ["M[ậa]c *M[ôo]n", "MM[ÔO]n"], "Ê The": ["[ÊE] *The"], "Mô Rô Ni": ["M[ôo] *R[ôo] *Ni","MRN[ÎI]"], "Giáo Lý và Giao Ước": ["Gi[áa]o *L[ýi] *v[àa] *Giao *[ƯU][ớo]c","GLG[ƯU]"], "Môi Se": ["M[ôo]i *Se"], "Áp Ra Ham": ["[ÁA]p *Ra *Ham","ARH[ÂA]m"], "Joseph Smith—Ma Thi Ơ": ["Joseph *Smith—Ma *Thi *[ƠO]", "JS—MT[ƠO]"], "Joseph Smith—Lịch Sử": ["Joseph *Smith—L[ịi]ch *S[ửu]", "JS—LS"], "Những Tín Điều": ["Nh[ữu]ng *T[íi]n *[ĐD]i[ềe]u", "NT[ĐD]"]
|
|
292
|
+
"Sáng Thế": ["STK[yý]*", "Sáng Thế Ký","S[áa]ng[ -]*Th[ếe][ -]*(K[yý])*"], "Xuất Ê Díp Tô": ["X[ÊE]DT(K[ýy])*","X[úu]at[ -]*Ê[ -]*D[íi]p[ -]*T[ôo][ -]*(K[yý])*","Xu[ấa]t h[àa]nh[ -]*(k[yý])*"], "Lê Vi": ["L[êe][ -]*Vi[ -]*(K[yý])*","LV(K[ýy])*"], "Dân Số": ["DS(K[yý])*","D[âa]n[ -]*S[ốo][ -]*(K[yý])*"], "Phục Truyền Luật Lệ": ["PTLL(K[yý])*","Ph[úu]c[ -]*Truy[ềe]n[ -]*Lu[ậa]t[ -]*L[ệe][ -]*(K[yý])*"], "Giô Suê": ["Gi[ôo][ -]*Su[êe]"], "Các Quan Xét": ["C[áa]c[ -]*Quan[ -]*X[ée]t","QX[ée]t"], "Ru Tơ": ["Ru[ -]*T[ơo]"], "1 Sa Mu Ên": ["1[ -]*Sa[ -]*Mu[ -]*Ên","1[ -]*SM[EÊ]n"], "2 Sa Mu Ên": ["2[ -]*Sa[ -]*Mu[ -]*Ên","2[ -]*SM[EÊ]n"], "1 Các Vua": ["1[ -]*C[áa]c[ -]*Vua","1[ -]*Vua"], "2 Các Vua": ["2[ -]*C[áa]c[ -]*Vua","2[ -]*Vua"], "1 Sử Ký": ["1[ -]*S[ửu][ -]*K[yý]"], "2 Sử Ký": ["2[ -]*S[ửu][ -]*K[yý]"], "E Xơ Ra": ["E[ -]*X[ơo][ -]*Ra"], "Nê Hê Mi": ["N[êe][ -]*H[êe][ -]*Mi"], "Ê Xơ Tê": ["Ê[ -]*X[ơo][ -]*T[êe]"], "Gióp": ["Gi[óo]p"], "Thi Thiên": ["Th*i*[ -]*Thi[êe]n"], "Châm Ngôn": ["Ch[âa]m[ -]*Ng[ôo]n","CNg[ôo]n"], "Truyền Đạo": ["T[DĐ][aạ]o","Truy[ềe]n[ -]*[ĐD]a[ọo]"], "Nhã Ca": ["Nh[ãa][ -]*Ca"], "Ê Sai": ["[ÊE][ -]*Sai"], "Giê Rê Mi": ["GRMi","Gi[êe][ -]*R[êe][ -]*Mi"], "Ca Thương": ["CTh[uư][oơ]ng","Ca[ -]*Th[ưu]ng"], "Ê Xê Chi Ên": ["[EÊ]XC[EÊ]n","Ê[ -]*X[êe][ -]*Chi[ -]*[ÊE]n"], "Đa Ni Ên": ["[DĐ]N[EÊ]n","[ĐD]a[ -]*Ni[ -]*[ÊE]n"], "Ô Sê": ["[ÔO][ -]*S[êe]"], "Giô Ên": ["Gi[ôo][ -]*[ÊE]n"], "A Mốt": ["A[ -]*M[ốo]t"], "Áp Đia": ["[ÁA]p[ -]*Đia"], "Giô Na": ["Gi[ôo][ -]*Na"], "Mi Chê": ["Mi[ -]*Ch[êe]"], "Na Hum": ["Na[ -]*Hum"], "Ha Ba Cúc": ["HBCuc","Ha[ -]*Ba[ -]*C[úu]c"], "Sô Phô Ni": ["S[ôo]*[ -]*Ph*[ôo]*[ -]*Ni"], "A Ghê": ["A[ -]*Gh[êe]"], "Xa Cha Ri": ["Xa*[ -]*Ch*a*[ -]*Ri"], "Ma La Chi": ["Ma*[ -]*La*[ -]*Chi"],
|
|
293
|
+
"Ma Thi Ơ": ["Ma[ -]*Thi[ -]*[ƠO]","MT[OƠ]"], "Mác": ["M[áa]c"], "Lu Ca": ["Lu[ -]*Ca"], "Giăng": ["Gio*[ăa]ng*"], "Công Vụ Các Sứ Đồ": ["C[ôo]ng[ -]*Vụ[ -]*C[áa]c[ -]*Sứ[ -]*Đ[ồo]", "CVCS[ĐD]"], "Rô Ma": ["R[ôo][ -]*Ma"], "1 Cô Rinh Tô": ["1[ -]*C[ôo]*[ -]*Ri*n*h*[ -]*T[ôo]"], "2 Cô Rinh Tô": ["2[ -]*C[ôo]*[ -]*Ri*n*h*[ -]*T[ôo]"], "Ga La Ti": ["Ga[ -]*La[ -]*Ti"], "Ê Phê Sô": ["[ÊE][ -]*Ph[êe][ -]*S[ôo]","[ÊE]PS[ÔO]"], "Phi Líp": ["Phi[ -]*L[íi]p"], "Cô Lô Se": ["C[ôo][ -]*L[ôo][ -]*Se","CL[ÔO]*Se"], "1 Tê Sa Lô Ni Ca": ["1[ -]*Tê[ -]*Sa[ -]*L[ôo][ -]*Ni[ -]*Ca","1[ -]*TSLN[ÔO]Ca","1 TSLNCa"], "2 Tê Sa Lô Ni Ca": ["2 TSLNCa","2[ -]*Tê[ -]*Sa[ -]*L[ôo][ -]*Ni[ -]*Ca","2[ -]*TSLN[ÔO]Ca"], "1 Ti Mô Thê": ["1[ -]*Ti[ -]*Mô[ -]*Th[êe]","1[ -]*TMTh[ÊE]"], "2 Ti Mô Thê": ["2[ -]*Ti[ -]*Mô[ -]*Th[êe]","2[ -]*TMTh[ÊE]"], "Tít": ["T[íi]t"], "Phi Lê Môn": ["Phi[ -]*L[êe][ -]*Môn","PL[ÊE]M[ÔO]n","PLM[oô]n"], "Hê Bơ Rơ": ["H[êe][ -]*Bơ[ -]*Rơ","HBR[ƠO]"], "Gia Cơ": ["GLTi", "Gia[ -]*C[ơo]"], "1 Phi E Rơ": ["1[ -]*Phi[ -]*E[ -]*R[ơo]","1[ -]*PER[ƠO]"], "2 Phi E Rơ": ["2[ -]*Phi[ -]*E[ -]*R[ơo]","2[ -]*PER[ƠO]"], "1 Giăng": ["1[ -]*Gio*[ăa]ng*"], "2 Giăng": ["2[ -]*Gio*[ăa]ng*"], "3 Giăng": ["3[ -]*Gio*[ăa]ng*"], "Giu Đe": ["Giu[ -]*[ĐD]e"], "Khải Huyền": ["Kh[ảa]i[ -]*Huy[ềe]n","KHuy[ềe]n"], "1 Nê Phi": ["1[ -]*N[êe][ -]*Phi"], "2 Nê Phi": ["2[ -]*N[êe][ -]*Phi"], "Gia Cốp": ["Gi*a*[ -]*C[ốo]p"], "Ê Nót": ["[ÊE][ -]*N[óo]t"], "Gia Rôm": ["Gi*a*[ -]*R[ôo]m"], "Ôm Ni": ["[ÔO]m[ -]*Ni"], "Lời Mặc Môn": ["L[ờo]i[ -]*M[ặa]c[ -]*M[ôo]n","LMM[ÔO]n"], "Mô Si A": ["M[ôo][ -]*Si[ -]*A"], "An Ma": ["An[ -]*Ma"], "Hê La Man": ["H[êe]*[ -]*La*[ -]*Man"], "3 Nê Phi": ["3[ -]*N[êe][ -]*Phi"], "4 Nê Phi": ["4[ -]*N[êe][ -]*Phi"], "Mặc Môn": ["M[ậa]c[ -]*M[ôo]n", "MM[ÔO]n"], "Ê The": ["[ÊE][ -]*The"], "Mô Rô Ni": ["M[ôo][ -]*R[ôo][ -]*Ni","MRN[ÎI]"], "Giáo Lý và Giao Ước": ["Gi[áa]o[ -]*L[ýi][ -]*v[àa][ -]*Giao[ -]*[ƯU][ớo]c","GLG[ƯU]"], "Môi Se": ["M[ôo]i[ -]*Se"], "Áp Ra Ham": ["[ÁA]p[ -]*Ra[ -]*Ham","ARH[ÂA]m"], "Joseph Smith—Ma Thi Ơ": ["Joseph[ -]*Smith—Ma[ -]*Thi[ -]*[ƠO]", "JS—MT[ƠO]"], "Joseph Smith—Lịch Sử": ["Joseph[ -]*Smith—L[ịi]ch[ -]*S[ửu]", "JS—LS"], "Những Tín Điều": ["Nh[ữu]ng[ -]*T[íi]n[ -]*[ĐD]i[ềe]u", "NT[ĐD]"]
|
|
294
294
|
},
|
|
295
295
|
matchRules:{
|
|
296
296
|
book: `(Thứ nhất|I|1|Thứ hai|II|2|Thứ ba|III|3|Thứ tư|IV|4)*\\s*(Sách* của)*\\s*`,
|
|
@@ -647,26 +647,59 @@ const raw_lang = {
|
|
|
647
647
|
}
|
|
648
648
|
;
|
|
649
649
|
const findMatchingBooks = (content,books) => {
|
|
650
|
-
const matchingBooks = books.filter(
|
|
650
|
+
const matchingBooks = books.filter(book => {
|
|
651
|
+
try {
|
|
652
|
+
// For Vietnamese and other languages, handle more flexible matching
|
|
653
|
+
let pattern = book;
|
|
654
|
+
|
|
655
|
+
// Replace * with optional space/separator patterns
|
|
656
|
+
pattern = pattern.replace(/\*/g, '');
|
|
657
|
+
|
|
658
|
+
// Make separators very flexible - handle spaces, hyphens, dots, etc.
|
|
659
|
+
pattern = pattern.replace(/[\s\-–—\.]+/g, '[\\s\\-–—\\.]*');
|
|
660
|
+
|
|
661
|
+
const regex = new RegExp(pattern, "ig");
|
|
662
|
+
const result = regex.test(content);
|
|
663
|
+
|
|
664
|
+
return result;
|
|
665
|
+
} catch (e) {
|
|
666
|
+
// Fallback to original logic if regex fails
|
|
667
|
+
return (new RegExp(book,"ig")).test(content);
|
|
668
|
+
}
|
|
669
|
+
});
|
|
651
670
|
return matchingBooks;
|
|
652
671
|
}
|
|
653
672
|
|
|
654
673
|
const findMatches = (content,books,lang_extra) => {
|
|
674
|
+
// Pre-process content to normalize HTML entities to Unicode dashes
|
|
675
|
+
const htmlEntityMap = {
|
|
676
|
+
'–': '–',
|
|
677
|
+
'—': '—',
|
|
678
|
+
'−': '–', // Treat minus as en dash for scripture ranges
|
|
679
|
+
'–': '–',
|
|
680
|
+
'—': '—',
|
|
681
|
+
'−': '–' // Treat minus as en dash for scripture ranges
|
|
682
|
+
};
|
|
683
|
+
|
|
684
|
+
let normalizedContent = content;
|
|
685
|
+
Object.entries(htmlEntityMap).forEach(([entity, unicode]) => {
|
|
686
|
+
normalizedContent = normalizedContent.replace(new RegExp(entity, 'g'), unicode);
|
|
687
|
+
});
|
|
655
688
|
|
|
656
689
|
const tail = lang_extra.tail ? new RegExp(lang_extra.tail,"ig") : /[^0-9]+$/;
|
|
657
690
|
const preBookMatch = lang_extra.book || `(First|I|1|1st|Second|II|2|2nd|Third|III|3|3rd|Fourth|IV|4|4th)*\\s*(books* of)*\\s*`;
|
|
658
|
-
const matchingBooks = findMatchingBooks(
|
|
659
|
-
const postBookMatch = lang_extra.chapter || "([0-9:.;,~ —–-]|cf
|
|
660
|
-
const fullBookMatches = matchingBooks.map(bookMatch=>{
|
|
691
|
+
const matchingBooks = findMatchingBooks(normalizedContent,books);
|
|
692
|
+
const postBookMatch = lang_extra.chapter || "([0-9:.;,~ —–-]|cf)*[0-9]+";
|
|
693
|
+
const fullBookMatches = matchingBooks.map(bookMatch=>{
|
|
661
694
|
const patternString = preBookMatch + bookMatch ;
|
|
662
695
|
const pattern = (new RegExp(patternString,"ig"));
|
|
663
|
-
const stringMatch = pattern.test(
|
|
696
|
+
const stringMatch = pattern.test(normalizedContent) ? patternString : null;
|
|
664
697
|
//console.log({pattern,content,stringMatch});
|
|
665
698
|
return stringMatch;
|
|
666
699
|
}).filter(x=>!!x);
|
|
667
700
|
|
|
668
701
|
const bookSubStrings = fullBookMatches.map(bookMatch=>{
|
|
669
|
-
const substrings =
|
|
702
|
+
const substrings = normalizedContent.match(new RegExp(bookMatch,"ig")).flat();
|
|
670
703
|
return substrings;
|
|
671
704
|
}).flat().reduce((prev,current)=>{
|
|
672
705
|
if(prev.includes(current)) return prev;
|
|
@@ -674,13 +707,13 @@ const fullBookMatches = matchingBooks.map(bookMatch=>{
|
|
|
674
707
|
},[]).filter(i=>!!i).map(substring=>{
|
|
675
708
|
substring = substring.trim();
|
|
676
709
|
let positions = [];
|
|
677
|
-
let index =
|
|
710
|
+
let index = normalizedContent.indexOf(substring);
|
|
678
711
|
while (index != -1) {
|
|
679
712
|
positions.push(index);
|
|
680
|
-
index =
|
|
713
|
+
index = normalizedContent.indexOf(substring, index + 1);
|
|
681
714
|
} return [substring,positions];
|
|
682
715
|
}).map(([substring,positions])=>{
|
|
683
|
-
const preChars = positions.map(i=>
|
|
716
|
+
const preChars = positions.map(i=>normalizedContent.substring(i-1,i));
|
|
684
717
|
positions = positions.filter((i,index)=>{
|
|
685
718
|
const charRightBeforeMatch = preChars[index];
|
|
686
719
|
const leadingCharIsInvalid = !/^(\s|\W|)$/.test(charRightBeforeMatch);
|
|
@@ -698,7 +731,7 @@ const fullBookMatches = matchingBooks.map(bookMatch=>{
|
|
|
698
731
|
}catch(e){
|
|
699
732
|
return null;
|
|
700
733
|
}
|
|
701
|
-
const match =
|
|
734
|
+
const match = normalizedContent.slice(i).match(pattern)?.[0]?.replace(tail,"").trim();
|
|
702
735
|
if(!match) return null;
|
|
703
736
|
const len = match.length;
|
|
704
737
|
const pos = i;
|
|
@@ -711,12 +744,12 @@ const fullBookMatches = matchingBooks.map(bookMatch=>{
|
|
|
711
744
|
const overLappingItems = possiblyOverlappingMatches.filter(([s,s1,e1])=>s!==string && s1<end && e1>end);
|
|
712
745
|
const hasOverlap = overLappingItems.length > 0;
|
|
713
746
|
const newEnd = hasOverlap ? Math.min(...overLappingItems.map(([s,s1,e1])=>s1)) : end;
|
|
714
|
-
const newString =
|
|
747
|
+
const newString = normalizedContent.slice(start,newEnd);
|
|
715
748
|
return newString.replace(tail,"").trim();
|
|
716
749
|
}).filter(i=>!!i);
|
|
717
750
|
const matches = matchesWithReferences.map(string=>{
|
|
718
751
|
const pattern = (new RegExp(string,"ig"));
|
|
719
|
-
const matches =
|
|
752
|
+
const matches = normalizedContent.match(pattern)?.map(i=>i.trim().replace(tail,""));
|
|
720
753
|
//console.log({string,matches,tail});
|
|
721
754
|
return matches;
|
|
722
755
|
}).flat()
|
|
@@ -724,7 +757,7 @@ const fullBookMatches = matchingBooks.map(bookMatch=>{
|
|
|
724
757
|
if(prev.includes(current)) return prev;
|
|
725
758
|
return [...prev,current]
|
|
726
759
|
},[]).filter(i=>!!i);
|
|
727
|
-
return matches;
|
|
760
|
+
return {matches, normalizedContent};
|
|
728
761
|
}
|
|
729
762
|
|
|
730
763
|
|
|
@@ -816,8 +849,8 @@ const processReferenceDetection = (content,books,lang_extra,lookupReference,call
|
|
|
816
849
|
{
|
|
817
850
|
try{
|
|
818
851
|
lang_extra = lang_extra || {};
|
|
819
|
-
const matches = findMatches(content,books,lang_extra);
|
|
820
|
-
const matchIndeces = findMatchIndexes(
|
|
852
|
+
const {matches, normalizedContent} = findMatches(content,books,lang_extra);
|
|
853
|
+
const matchIndeces = findMatchIndexes(normalizedContent,matches,lookupReference,lang_extra);
|
|
821
854
|
if(!matchIndeces) return content;
|
|
822
855
|
const gapsBetweenIndeces = matchIndeces.reduce((prev,current,index)=>{
|
|
823
856
|
if(index === 0) return prev;
|
|
@@ -825,7 +858,7 @@ const processReferenceDetection = (content,books,lang_extra,lookupReference,call
|
|
|
825
858
|
const gap = [lastPair[1],current[0]];
|
|
826
859
|
return [...prev,gap];
|
|
827
860
|
},[]);
|
|
828
|
-
const gapStrings = gapsBetweenIndeces.map(([start,end])=>
|
|
861
|
+
const gapStrings = gapsBetweenIndeces.map(([start,end])=>normalizedContent.substring(start,end).trim());
|
|
829
862
|
//console.log({matches,matchIndeces,gapsBetweenIndeces,gapStrings});
|
|
830
863
|
const joiners = lang_extra.joiners || ["^[;, ]*(and|c\\.*f\\.*)*$"];
|
|
831
864
|
const gapThatMayBeMerged = gapsBetweenIndeces.map(([start,end],i)=>{
|
|
@@ -874,11 +907,11 @@ const processReferenceDetection = (content,books,lang_extra,lookupReference,call
|
|
|
874
907
|
|
|
875
908
|
//check content between matches. If puctuation only (or 'and'), then merge
|
|
876
909
|
const cutItems = mergedIndeces.map(([start,end])=>{
|
|
877
|
-
const string =
|
|
910
|
+
const string = normalizedContent.substring(start,end);
|
|
878
911
|
return lookupReference(string).query
|
|
879
912
|
}).map(callback);
|
|
880
913
|
|
|
881
|
-
const negativeItems = negativeSpace.map(([start,end])=>
|
|
914
|
+
const negativeItems = negativeSpace.map(([start,end])=>normalizedContent.substring(start,end));
|
|
882
915
|
const firstReferenceIsAtStart = mergedIndeces[0][0] === 0;
|
|
883
916
|
const maxCount = Math.max(cutItems.length,negativeItems.length);
|
|
884
917
|
//merge by alternating cutItems and negativeItems. run the callback on the cut items
|
package/dist/scriptures.mjs
CHANGED
|
@@ -167,8 +167,8 @@ const raw_regex_orig = {
|
|
|
167
167
|
["([0-9]),*\\s*\\b(?:chapt*ers*|ch|chptrs*)\\.*,*\\s*([0-9])", "$1:$2"],
|
|
168
168
|
["([a-z]),*\\s*\\b(?:chapt*ers*|ch|chptrs*)\\s*([0-9])", "$1 $2"],
|
|
169
169
|
["[()]+", " "],
|
|
170
|
+
["(?:&(?:ndash|mdash|minus)|&#(?:8211|8212|8722))", "-"],
|
|
170
171
|
["[\\s.]*[–—−\\-]+[\\s.]*", "-"],
|
|
171
|
-
["–", "-"],
|
|
172
172
|
["([;,])\\s*and\\s*", "$1"],
|
|
173
173
|
["([0-9])[ .]*and[ .]*", "$1,"],
|
|
174
174
|
["(\\d)(\\.|: )(\\d)", "$1:$3"],
|
|
@@ -289,8 +289,8 @@ const raw_lang = {
|
|
|
289
289
|
[";\\s*Giao", "và Giao"],
|
|
290
290
|
],
|
|
291
291
|
books:{
|
|
292
|
-
"Sáng Thế": ["STK[yý]", "Sáng Thế Ký","S[áa]ng *Th[ếe] *(K[yý])*"], "Xuất Ê Díp Tô": ["X[ÊE]DT(K[ýy])*","X[úu]at *Ê *D[íi]p *T[ôo] *(K[yý])*","Xu[ấa]t h[àa]nh *(k[yý])*"], "Lê Vi": ["L[êe] *Vi *(K[yý])*","LV(K[ýy])*"], "Dân Số": ["DS(K[yý])*","D[âa]n *S[ốo] *(K[yý])*"], "Phục Truyền Luật Lệ": ["PTLL(K[yý])*","Ph[úu]c *Truy[ềe]n *Lu[ậa]t *L[ệe] *(K[yý])*"], "Giô Suê": ["Gi[ôo] *Su[êe]"], "Các Quan Xét": ["C[áa]c *Quan *X[ée]t","QX[ée]t"], "Ru Tơ": ["Ru *T[ơo]"], "1 Sa Mu Ên": ["1 *Sa *Mu *Ên","1 *SM[EÊ]n"], "2 Sa Mu Ên": ["2 *Sa *Mu *Ên","2 *SM[EÊ]n"], "1 Các Vua": ["1 *C[áa]c *Vua","1 *Vua"], "2 Các Vua": ["2 *C[áa]c *Vua","2 *Vua"], "1 Sử Ký": ["1 *S[ửu] *K[yý]"], "2 Sử Ký": ["2 *S[ửu] *K[yý]"], "E Xơ Ra": ["E *X[ơo] *Ra"], "Nê Hê Mi": ["N[êe] *H[êe] *Mi"], "Ê Xơ Tê": ["Ê *X[ơo] *T[êe]"], "Gióp": ["Gi[óo]p"], "Thi Thiên": ["Th*i* *Thi[êe]n"], "Châm Ngôn": ["Ch[âa]m *Ng[ôo]n","CNg[ôo]n"], "Truyền Đạo": ["T[DĐ][aạ]o","Truy[ềe]n *[ĐD]a[ọo]"], "Nhã Ca": ["Nh[ãa] *Ca"], "Ê Sai": ["[ÊE] *Sai"], "Giê Rê Mi": ["GRMi","Gi[êe] *R[êe] *Mi"], "Ca Thương": ["CTh[uư][oơ]ng","Ca *Th[ưu]ng"], "Ê Xê Chi Ên": ["[EÊ]XC[EÊ]n","Ê *X[êe] *Chi *[ÊE]n"], "Đa Ni Ên": ["[DĐ]N[EÊ]n","[ĐD]a *Ni *[ÊE]n"], "Ô Sê": ["[ÔO] *S[êe]"], "Giô Ên": ["Gi[ôo] *[ÊE]n"], "A Mốt": ["A *M[ốo]t"], "Áp Đia": ["[ÁA]p *Đia"], "Giô Na": ["Gi[ôo] *Na"], "Mi Chê": ["Mi *Ch[êe]"], "Na Hum": ["Na *Hum"], "Ha Ba Cúc": ["HBCuc","Ha *Ba *C[úu]c"], "Sô Phô Ni": ["S[ôo]* *Ph*[ôo]* *Ni"], "A Ghê": ["A *Gh[êe]"], "Xa Cha Ri": ["Xa* *Ch*a* *Ri"], "Ma La Chi": ["Ma* *La* *Chi"],
|
|
293
|
-
"Ma Thi Ơ": ["Ma *Thi *[ƠO]","MT[OƠ]"], "Mác": ["M[áa]c"], "Lu Ca": ["Lu *Ca"], "Giăng": ["Gio*[ăa]ng*"], "Công Vụ Các Sứ Đồ": ["C[ôo]ng *Vụ *C[áa]c *Sứ *Đ[ồo]", "CVCS[ĐD]"], "Rô Ma": ["R[ôo] *Ma"], "1 Cô Rinh Tô": ["1 *C[ôo]* *Ri*n*h* *T[ôo]"], "2 Cô Rinh Tô": ["2 *C[ôo]* *Ri*n*h* *T[ôo]"], "Ga La Ti": ["Ga *La *Ti"], "Ê Phê Sô": ["[ÊE] *Ph[êe] *S[ôo]","[ÊE]PS[ÔO]"], "Phi Líp": ["Phi *L[íi]p"], "Cô Lô Se": ["C[ôo] *L[ôo] *Se","CL[ÔO]*Se"], "1 Tê Sa Lô Ni Ca": ["1 *Tê *Sa *L[ôo] *Ni *Ca","1 *TSLN[ÔO]Ca","1 TSLNCa"], "2 Tê Sa Lô Ni Ca": ["2 TSLNCa","2 *Tê *Sa *L[ôo] *Ni *Ca","2 *TSLN[ÔO]Ca"], "1 Ti Mô Thê": ["1 *Ti *Mô *Th[êe]","1 *TMTh[ÊE]"], "2 Ti Mô Thê": ["2 *Ti *Mô *Th[êe]","2 *TMTh[ÊE]"], "Tít": ["T[íi]t"], "Phi Lê Môn": ["Phi *L[êe] *Môn","PL[ÊE]M[ÔO]n","PLM[oô]n"], "Hê Bơ Rơ": ["H[êe] *Bơ *Rơ","HBR[ƠO]"], "Gia Cơ": ["GLTi", "Gia *C[ơo]"], "1 Phi E Rơ": ["1 *Phi *E *R[ơo]","1 *PER[ƠO]"], "2 Phi E Rơ": ["2 *Phi *E *R[ơo]","2 *PER[ƠO]"], "1 Giăng": ["1 *Gio*[ăa]ng*"], "2 Giăng": ["2 *Gio*[ăa]ng*"], "3 Giăng": ["3 *Gio*[ăa]ng*"], "Giu Đe": ["Giu *[ĐD]e"], "Khải Huyền": ["Kh[ảa]i *Huy[ềe]n","KHuy[ềe]n"], "1 Nê Phi": ["1 *N[êe] *Phi"], "2 Nê Phi": ["2 *N[êe] *Phi"], "Gia Cốp": ["Gi*a* *C[ốo]p"], "Ê Nót": ["[ÊE] *N[óo]t"], "Gia Rôm": ["Gi*a* *R[ôo]m"], "Ôm Ni": ["[ÔO]m *Ni"], "Lời Mặc Môn": ["L[ờo]i *M[ặa]c *M[ôo]n","LMM[ÔO]n"], "Mô Si A": ["M[ôo] *Si *A"], "An Ma": ["An *Ma"], "Hê La Man": ["H[êe]* *La* *Man"], "3 Nê Phi": ["3 *N[êe] *Phi"], "4 Nê Phi": ["4 *N[êe] *Phi"], "Mặc Môn": ["M[ậa]c *M[ôo]n", "MM[ÔO]n"], "Ê The": ["[ÊE] *The"], "Mô Rô Ni": ["M[ôo] *R[ôo] *Ni","MRN[ÎI]"], "Giáo Lý và Giao Ước": ["Gi[áa]o *L[ýi] *v[àa] *Giao *[ƯU][ớo]c","GLG[ƯU]"], "Môi Se": ["M[ôo]i *Se"], "Áp Ra Ham": ["[ÁA]p *Ra *Ham","ARH[ÂA]m"], "Joseph Smith—Ma Thi Ơ": ["Joseph *Smith—Ma *Thi *[ƠO]", "JS—MT[ƠO]"], "Joseph Smith—Lịch Sử": ["Joseph *Smith—L[ịi]ch *S[ửu]", "JS—LS"], "Những Tín Điều": ["Nh[ữu]ng *T[íi]n *[ĐD]i[ềe]u", "NT[ĐD]"]
|
|
292
|
+
"Sáng Thế": ["STK[yý]*", "Sáng Thế Ký","S[áa]ng[ -]*Th[ếe][ -]*(K[yý])*"], "Xuất Ê Díp Tô": ["X[ÊE]DT(K[ýy])*","X[úu]at[ -]*Ê[ -]*D[íi]p[ -]*T[ôo][ -]*(K[yý])*","Xu[ấa]t h[àa]nh[ -]*(k[yý])*"], "Lê Vi": ["L[êe][ -]*Vi[ -]*(K[yý])*","LV(K[ýy])*"], "Dân Số": ["DS(K[yý])*","D[âa]n[ -]*S[ốo][ -]*(K[yý])*"], "Phục Truyền Luật Lệ": ["PTLL(K[yý])*","Ph[úu]c[ -]*Truy[ềe]n[ -]*Lu[ậa]t[ -]*L[ệe][ -]*(K[yý])*"], "Giô Suê": ["Gi[ôo][ -]*Su[êe]"], "Các Quan Xét": ["C[áa]c[ -]*Quan[ -]*X[ée]t","QX[ée]t"], "Ru Tơ": ["Ru[ -]*T[ơo]"], "1 Sa Mu Ên": ["1[ -]*Sa[ -]*Mu[ -]*Ên","1[ -]*SM[EÊ]n"], "2 Sa Mu Ên": ["2[ -]*Sa[ -]*Mu[ -]*Ên","2[ -]*SM[EÊ]n"], "1 Các Vua": ["1[ -]*C[áa]c[ -]*Vua","1[ -]*Vua"], "2 Các Vua": ["2[ -]*C[áa]c[ -]*Vua","2[ -]*Vua"], "1 Sử Ký": ["1[ -]*S[ửu][ -]*K[yý]"], "2 Sử Ký": ["2[ -]*S[ửu][ -]*K[yý]"], "E Xơ Ra": ["E[ -]*X[ơo][ -]*Ra"], "Nê Hê Mi": ["N[êe][ -]*H[êe][ -]*Mi"], "Ê Xơ Tê": ["Ê[ -]*X[ơo][ -]*T[êe]"], "Gióp": ["Gi[óo]p"], "Thi Thiên": ["Th*i*[ -]*Thi[êe]n"], "Châm Ngôn": ["Ch[âa]m[ -]*Ng[ôo]n","CNg[ôo]n"], "Truyền Đạo": ["T[DĐ][aạ]o","Truy[ềe]n[ -]*[ĐD]a[ọo]"], "Nhã Ca": ["Nh[ãa][ -]*Ca"], "Ê Sai": ["[ÊE][ -]*Sai"], "Giê Rê Mi": ["GRMi","Gi[êe][ -]*R[êe][ -]*Mi"], "Ca Thương": ["CTh[uư][oơ]ng","Ca[ -]*Th[ưu]ng"], "Ê Xê Chi Ên": ["[EÊ]XC[EÊ]n","Ê[ -]*X[êe][ -]*Chi[ -]*[ÊE]n"], "Đa Ni Ên": ["[DĐ]N[EÊ]n","[ĐD]a[ -]*Ni[ -]*[ÊE]n"], "Ô Sê": ["[ÔO][ -]*S[êe]"], "Giô Ên": ["Gi[ôo][ -]*[ÊE]n"], "A Mốt": ["A[ -]*M[ốo]t"], "Áp Đia": ["[ÁA]p[ -]*Đia"], "Giô Na": ["Gi[ôo][ -]*Na"], "Mi Chê": ["Mi[ -]*Ch[êe]"], "Na Hum": ["Na[ -]*Hum"], "Ha Ba Cúc": ["HBCuc","Ha[ -]*Ba[ -]*C[úu]c"], "Sô Phô Ni": ["S[ôo]*[ -]*Ph*[ôo]*[ -]*Ni"], "A Ghê": ["A[ -]*Gh[êe]"], "Xa Cha Ri": ["Xa*[ -]*Ch*a*[ -]*Ri"], "Ma La Chi": ["Ma*[ -]*La*[ -]*Chi"],
|
|
293
|
+
"Ma Thi Ơ": ["Ma[ -]*Thi[ -]*[ƠO]","MT[OƠ]"], "Mác": ["M[áa]c"], "Lu Ca": ["Lu[ -]*Ca"], "Giăng": ["Gio*[ăa]ng*"], "Công Vụ Các Sứ Đồ": ["C[ôo]ng[ -]*Vụ[ -]*C[áa]c[ -]*Sứ[ -]*Đ[ồo]", "CVCS[ĐD]"], "Rô Ma": ["R[ôo][ -]*Ma"], "1 Cô Rinh Tô": ["1[ -]*C[ôo]*[ -]*Ri*n*h*[ -]*T[ôo]"], "2 Cô Rinh Tô": ["2[ -]*C[ôo]*[ -]*Ri*n*h*[ -]*T[ôo]"], "Ga La Ti": ["Ga[ -]*La[ -]*Ti"], "Ê Phê Sô": ["[ÊE][ -]*Ph[êe][ -]*S[ôo]","[ÊE]PS[ÔO]"], "Phi Líp": ["Phi[ -]*L[íi]p"], "Cô Lô Se": ["C[ôo][ -]*L[ôo][ -]*Se","CL[ÔO]*Se"], "1 Tê Sa Lô Ni Ca": ["1[ -]*Tê[ -]*Sa[ -]*L[ôo][ -]*Ni[ -]*Ca","1[ -]*TSLN[ÔO]Ca","1 TSLNCa"], "2 Tê Sa Lô Ni Ca": ["2 TSLNCa","2[ -]*Tê[ -]*Sa[ -]*L[ôo][ -]*Ni[ -]*Ca","2[ -]*TSLN[ÔO]Ca"], "1 Ti Mô Thê": ["1[ -]*Ti[ -]*Mô[ -]*Th[êe]","1[ -]*TMTh[ÊE]"], "2 Ti Mô Thê": ["2[ -]*Ti[ -]*Mô[ -]*Th[êe]","2[ -]*TMTh[ÊE]"], "Tít": ["T[íi]t"], "Phi Lê Môn": ["Phi[ -]*L[êe][ -]*Môn","PL[ÊE]M[ÔO]n","PLM[oô]n"], "Hê Bơ Rơ": ["H[êe][ -]*Bơ[ -]*Rơ","HBR[ƠO]"], "Gia Cơ": ["GLTi", "Gia[ -]*C[ơo]"], "1 Phi E Rơ": ["1[ -]*Phi[ -]*E[ -]*R[ơo]","1[ -]*PER[ƠO]"], "2 Phi E Rơ": ["2[ -]*Phi[ -]*E[ -]*R[ơo]","2[ -]*PER[ƠO]"], "1 Giăng": ["1[ -]*Gio*[ăa]ng*"], "2 Giăng": ["2[ -]*Gio*[ăa]ng*"], "3 Giăng": ["3[ -]*Gio*[ăa]ng*"], "Giu Đe": ["Giu[ -]*[ĐD]e"], "Khải Huyền": ["Kh[ảa]i[ -]*Huy[ềe]n","KHuy[ềe]n"], "1 Nê Phi": ["1[ -]*N[êe][ -]*Phi"], "2 Nê Phi": ["2[ -]*N[êe][ -]*Phi"], "Gia Cốp": ["Gi*a*[ -]*C[ốo]p"], "Ê Nót": ["[ÊE][ -]*N[óo]t"], "Gia Rôm": ["Gi*a*[ -]*R[ôo]m"], "Ôm Ni": ["[ÔO]m[ -]*Ni"], "Lời Mặc Môn": ["L[ờo]i[ -]*M[ặa]c[ -]*M[ôo]n","LMM[ÔO]n"], "Mô Si A": ["M[ôo][ -]*Si[ -]*A"], "An Ma": ["An[ -]*Ma"], "Hê La Man": ["H[êe]*[ -]*La*[ -]*Man"], "3 Nê Phi": ["3[ -]*N[êe][ -]*Phi"], "4 Nê Phi": ["4[ -]*N[êe][ -]*Phi"], "Mặc Môn": ["M[ậa]c[ -]*M[ôo]n", "MM[ÔO]n"], "Ê The": ["[ÊE][ -]*The"], "Mô Rô Ni": ["M[ôo][ -]*R[ôo][ -]*Ni","MRN[ÎI]"], "Giáo Lý và Giao Ước": ["Gi[áa]o[ -]*L[ýi][ -]*v[àa][ -]*Giao[ -]*[ƯU][ớo]c","GLG[ƯU]"], "Môi Se": ["M[ôo]i[ -]*Se"], "Áp Ra Ham": ["[ÁA]p[ -]*Ra[ -]*Ham","ARH[ÂA]m"], "Joseph Smith—Ma Thi Ơ": ["Joseph[ -]*Smith—Ma[ -]*Thi[ -]*[ƠO]", "JS—MT[ƠO]"], "Joseph Smith—Lịch Sử": ["Joseph[ -]*Smith—L[ịi]ch[ -]*S[ửu]", "JS—LS"], "Những Tín Điều": ["Nh[ữu]ng[ -]*T[íi]n[ -]*[ĐD]i[ềe]u", "NT[ĐD]"]
|
|
294
294
|
},
|
|
295
295
|
matchRules:{
|
|
296
296
|
book: `(Thứ nhất|I|1|Thứ hai|II|2|Thứ ba|III|3|Thứ tư|IV|4)*\\s*(Sách* của)*\\s*`,
|
|
@@ -647,26 +647,59 @@ const raw_lang = {
|
|
|
647
647
|
}
|
|
648
648
|
;
|
|
649
649
|
const findMatchingBooks = (content,books) => {
|
|
650
|
-
const matchingBooks = books.filter(
|
|
650
|
+
const matchingBooks = books.filter(book => {
|
|
651
|
+
try {
|
|
652
|
+
// For Vietnamese and other languages, handle more flexible matching
|
|
653
|
+
let pattern = book;
|
|
654
|
+
|
|
655
|
+
// Replace * with optional space/separator patterns
|
|
656
|
+
pattern = pattern.replace(/\*/g, '');
|
|
657
|
+
|
|
658
|
+
// Make separators very flexible - handle spaces, hyphens, dots, etc.
|
|
659
|
+
pattern = pattern.replace(/[\s\-–—\.]+/g, '[\\s\\-–—\\.]*');
|
|
660
|
+
|
|
661
|
+
const regex = new RegExp(pattern, "ig");
|
|
662
|
+
const result = regex.test(content);
|
|
663
|
+
|
|
664
|
+
return result;
|
|
665
|
+
} catch (e) {
|
|
666
|
+
// Fallback to original logic if regex fails
|
|
667
|
+
return (new RegExp(book,"ig")).test(content);
|
|
668
|
+
}
|
|
669
|
+
});
|
|
651
670
|
return matchingBooks;
|
|
652
671
|
}
|
|
653
672
|
|
|
654
673
|
const findMatches = (content,books,lang_extra) => {
|
|
674
|
+
// Pre-process content to normalize HTML entities to Unicode dashes
|
|
675
|
+
const htmlEntityMap = {
|
|
676
|
+
'–': '–',
|
|
677
|
+
'—': '—',
|
|
678
|
+
'−': '–', // Treat minus as en dash for scripture ranges
|
|
679
|
+
'–': '–',
|
|
680
|
+
'—': '—',
|
|
681
|
+
'−': '–' // Treat minus as en dash for scripture ranges
|
|
682
|
+
};
|
|
683
|
+
|
|
684
|
+
let normalizedContent = content;
|
|
685
|
+
Object.entries(htmlEntityMap).forEach(([entity, unicode]) => {
|
|
686
|
+
normalizedContent = normalizedContent.replace(new RegExp(entity, 'g'), unicode);
|
|
687
|
+
});
|
|
655
688
|
|
|
656
689
|
const tail = lang_extra.tail ? new RegExp(lang_extra.tail,"ig") : /[^0-9]+$/;
|
|
657
690
|
const preBookMatch = lang_extra.book || `(First|I|1|1st|Second|II|2|2nd|Third|III|3|3rd|Fourth|IV|4|4th)*\\s*(books* of)*\\s*`;
|
|
658
|
-
const matchingBooks = findMatchingBooks(
|
|
659
|
-
const postBookMatch = lang_extra.chapter || "([0-9:.;,~ —–-]|cf
|
|
660
|
-
const fullBookMatches = matchingBooks.map(bookMatch=>{
|
|
691
|
+
const matchingBooks = findMatchingBooks(normalizedContent,books);
|
|
692
|
+
const postBookMatch = lang_extra.chapter || "([0-9:.;,~ —–-]|cf)*[0-9]+";
|
|
693
|
+
const fullBookMatches = matchingBooks.map(bookMatch=>{
|
|
661
694
|
const patternString = preBookMatch + bookMatch ;
|
|
662
695
|
const pattern = (new RegExp(patternString,"ig"));
|
|
663
|
-
const stringMatch = pattern.test(
|
|
696
|
+
const stringMatch = pattern.test(normalizedContent) ? patternString : null;
|
|
664
697
|
//console.log({pattern,content,stringMatch});
|
|
665
698
|
return stringMatch;
|
|
666
699
|
}).filter(x=>!!x);
|
|
667
700
|
|
|
668
701
|
const bookSubStrings = fullBookMatches.map(bookMatch=>{
|
|
669
|
-
const substrings =
|
|
702
|
+
const substrings = normalizedContent.match(new RegExp(bookMatch,"ig")).flat();
|
|
670
703
|
return substrings;
|
|
671
704
|
}).flat().reduce((prev,current)=>{
|
|
672
705
|
if(prev.includes(current)) return prev;
|
|
@@ -674,13 +707,13 @@ const fullBookMatches = matchingBooks.map(bookMatch=>{
|
|
|
674
707
|
},[]).filter(i=>!!i).map(substring=>{
|
|
675
708
|
substring = substring.trim();
|
|
676
709
|
let positions = [];
|
|
677
|
-
let index =
|
|
710
|
+
let index = normalizedContent.indexOf(substring);
|
|
678
711
|
while (index != -1) {
|
|
679
712
|
positions.push(index);
|
|
680
|
-
index =
|
|
713
|
+
index = normalizedContent.indexOf(substring, index + 1);
|
|
681
714
|
} return [substring,positions];
|
|
682
715
|
}).map(([substring,positions])=>{
|
|
683
|
-
const preChars = positions.map(i=>
|
|
716
|
+
const preChars = positions.map(i=>normalizedContent.substring(i-1,i));
|
|
684
717
|
positions = positions.filter((i,index)=>{
|
|
685
718
|
const charRightBeforeMatch = preChars[index];
|
|
686
719
|
const leadingCharIsInvalid = !/^(\s|\W|)$/.test(charRightBeforeMatch);
|
|
@@ -698,7 +731,7 @@ const fullBookMatches = matchingBooks.map(bookMatch=>{
|
|
|
698
731
|
}catch(e){
|
|
699
732
|
return null;
|
|
700
733
|
}
|
|
701
|
-
const match =
|
|
734
|
+
const match = normalizedContent.slice(i).match(pattern)?.[0]?.replace(tail,"").trim();
|
|
702
735
|
if(!match) return null;
|
|
703
736
|
const len = match.length;
|
|
704
737
|
const pos = i;
|
|
@@ -711,12 +744,12 @@ const fullBookMatches = matchingBooks.map(bookMatch=>{
|
|
|
711
744
|
const overLappingItems = possiblyOverlappingMatches.filter(([s,s1,e1])=>s!==string && s1<end && e1>end);
|
|
712
745
|
const hasOverlap = overLappingItems.length > 0;
|
|
713
746
|
const newEnd = hasOverlap ? Math.min(...overLappingItems.map(([s,s1,e1])=>s1)) : end;
|
|
714
|
-
const newString =
|
|
747
|
+
const newString = normalizedContent.slice(start,newEnd);
|
|
715
748
|
return newString.replace(tail,"").trim();
|
|
716
749
|
}).filter(i=>!!i);
|
|
717
750
|
const matches = matchesWithReferences.map(string=>{
|
|
718
751
|
const pattern = (new RegExp(string,"ig"));
|
|
719
|
-
const matches =
|
|
752
|
+
const matches = normalizedContent.match(pattern)?.map(i=>i.trim().replace(tail,""));
|
|
720
753
|
//console.log({string,matches,tail});
|
|
721
754
|
return matches;
|
|
722
755
|
}).flat()
|
|
@@ -724,7 +757,7 @@ const fullBookMatches = matchingBooks.map(bookMatch=>{
|
|
|
724
757
|
if(prev.includes(current)) return prev;
|
|
725
758
|
return [...prev,current]
|
|
726
759
|
},[]).filter(i=>!!i);
|
|
727
|
-
return matches;
|
|
760
|
+
return {matches, normalizedContent};
|
|
728
761
|
}
|
|
729
762
|
|
|
730
763
|
|
|
@@ -816,8 +849,8 @@ const processReferenceDetection = (content,books,lang_extra,lookupReference,call
|
|
|
816
849
|
{
|
|
817
850
|
try{
|
|
818
851
|
lang_extra = lang_extra || {};
|
|
819
|
-
const matches = findMatches(content,books,lang_extra);
|
|
820
|
-
const matchIndeces = findMatchIndexes(
|
|
852
|
+
const {matches, normalizedContent} = findMatches(content,books,lang_extra);
|
|
853
|
+
const matchIndeces = findMatchIndexes(normalizedContent,matches,lookupReference,lang_extra);
|
|
821
854
|
if(!matchIndeces) return content;
|
|
822
855
|
const gapsBetweenIndeces = matchIndeces.reduce((prev,current,index)=>{
|
|
823
856
|
if(index === 0) return prev;
|
|
@@ -825,7 +858,7 @@ const processReferenceDetection = (content,books,lang_extra,lookupReference,call
|
|
|
825
858
|
const gap = [lastPair[1],current[0]];
|
|
826
859
|
return [...prev,gap];
|
|
827
860
|
},[]);
|
|
828
|
-
const gapStrings = gapsBetweenIndeces.map(([start,end])=>
|
|
861
|
+
const gapStrings = gapsBetweenIndeces.map(([start,end])=>normalizedContent.substring(start,end).trim());
|
|
829
862
|
//console.log({matches,matchIndeces,gapsBetweenIndeces,gapStrings});
|
|
830
863
|
const joiners = lang_extra.joiners || ["^[;, ]*(and|c\\.*f\\.*)*$"];
|
|
831
864
|
const gapThatMayBeMerged = gapsBetweenIndeces.map(([start,end],i)=>{
|
|
@@ -874,11 +907,11 @@ const processReferenceDetection = (content,books,lang_extra,lookupReference,call
|
|
|
874
907
|
|
|
875
908
|
//check content between matches. If puctuation only (or 'and'), then merge
|
|
876
909
|
const cutItems = mergedIndeces.map(([start,end])=>{
|
|
877
|
-
const string =
|
|
910
|
+
const string = normalizedContent.substring(start,end);
|
|
878
911
|
return lookupReference(string).query
|
|
879
912
|
}).map(callback);
|
|
880
913
|
|
|
881
|
-
const negativeItems = negativeSpace.map(([start,end])=>
|
|
914
|
+
const negativeItems = negativeSpace.map(([start,end])=>normalizedContent.substring(start,end));
|
|
882
915
|
const firstReferenceIsAtStart = mergedIndeces[0][0] === 0;
|
|
883
916
|
const maxCount = Math.max(cutItems.length,negativeItems.length);
|
|
884
917
|
//merge by alternating cutItems and negativeItems. run the callback on the cut items
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "scripture-guide",
|
|
3
|
-
"version": "1.0.
|
|
3
|
+
"version": "1.0.82",
|
|
4
4
|
"description": "A utility for biblical and scripture reference parsing that enables structured queries based on strings of traditional scripture references (e.g. John 3:16). ",
|
|
5
5
|
"main": "dist/scriptures.cjs",
|
|
6
6
|
"module": "dist/scriptures.mjs",
|
|
@@ -53,5 +53,8 @@
|
|
|
53
53
|
"@babel/core": "^7.24.7",
|
|
54
54
|
"@babel/plugin-transform-modules-commonjs": "^7.27.1",
|
|
55
55
|
"@babel/preset-env": "^7.24.7"
|
|
56
|
+
},
|
|
57
|
+
"dependencies": {
|
|
58
|
+
"js-yaml": "^4.1.0"
|
|
56
59
|
}
|
|
57
60
|
}
|