codexparser 0.0.40 → 0.0.42

package/all-scripture-test.js

@@ -5,7 +5,9 @@ const text =
     "Joel 10:13 The passages Luke 2:32 and Lk 1:23 that we are looking at tonight 1 Cor 12:34 2 Cor 3:4 are found Jude 6, in Jude 5, Genesis 2:1 - 3:19, 1 John 3:16-17,  1 Peter 1:1, and Romans 10:13, 15, 17. Please turn in your Bibles. Ps 109:4,5,6,8.  Isaiah 61.2-3 Mt 5.4"
 const single = "Ge 27.27-29,32-40 Heb 11.20 Heb. 12.17 Jonah 3"
 const jd = "Jd. 5"
-const cor = "Hos 1:1-3, 8 Song of Solomon 1:2, Song of Songs 2:2. Ezek 17:3. Ezekiel 17:3"
+const cor = "Song of Solomon 1:2, Song of Songs 2:2. Ezek 17:3.  He 12:13-15 Hos 1:1-3, 8 "
 const passages = parser.parse(single + " " + text + " " + jd + " " + cor)
-console.log(passages.getPassages())
+passages.getPassages().forEach(passage => {
+    console.log(passage)    
+})
 //const passages = parser.parse('Romans 8:9,12,15,17,20,28')

package/package.json

@@ -1,11 +1,11 @@
 {
   "name": "codexparser",
-  "version": "0.0.40",
+  "version": "0.0.42",
   "description": "This is a Javascript Bible parser and text scanner. It will search through texts and collate all scripture references into an array and parse them into objects, and it will parse passages into objects by book, chapter, verse, and testament. ",
   "main": "index.js",
   "scripts": {
     "test": "echo \"Error: no test specified\" && exit 1",
-    "webpack": "webpack --mode=production", 
+    "webpack": "webpack --mode=production",
     "build": "browserify src/CodexParser.js -t  | uglifyjs > dist/CodexParser.js"
   },
   "author": "Jeremy Menicucci",
@@ -22,11 +22,12 @@
     "glob": "^10.4.1",
     "path": "^0.12.7",
     "uglify-es": "^3.3.9",
-    "uglifyify": "^5.0.2",
+    "uglifyify": "^5.0.0",
     "webpack": "^5.90.3",
     "webpack-cli": "^5.1.4"
   },
   "dependencies": {
-    "bible-passage-reference-parser": "^2.0.1"
+    "bible-passage-reference-parser": "^2.0.1",
+    "unidecode": "^1.1.0"
   }
 }

package/quicktest.js

@@ -0,0 +1,5 @@
+const BibleParser = require("./src/CodexParser.js")
+const string = "Genesis 1:1 He 4.4"
+const parser = new BibleParser()
+const result = parser.parse(string)
+console.log(result.getPassages())

package/src/CodexParser-javascript.js

@@ -0,0 +1,317 @@
+const books = [
+    "Gen",
+    "Ge",
+    "Gn",
+    "Exo",
+    "Ex",
+    "Exod",
+    "Lev",
+    "Le",
+    "Lv",
+    "Num",
+    "Nu",
+    "Nm",
+    "Nb",
+    "Deut",
+    "Dt",
+    "Josh",
+    "Jos",
+    "Jsh",
+    "Judg",
+    "Jdg",
+    "Jg",
+    "Jdgs",
+    "Rth",
+    "Ru",
+    "Sam",
+    "Samuel",
+    "Kings",
+    "Kgs",
+    "Kin",
+    "Chron",
+    "Chronicles",
+    "Ezra",
+    "Ezr",
+    "Ez",
+    "Neh",
+    "Ne",
+    "Esth",
+    "Es",
+    "Job",
+    "Job",
+    "Jb",
+    "Pslm",
+    "Ps",
+    "Psalms",
+    "Psa",
+    "Psm",
+    "Pss",
+    "Prov",
+    "Pr",
+    "Prv",
+    "Eccles",
+    "Ec",
+    "Song",
+    "So",
+    "Canticles",
+    "Song of Songs",
+    "SOS",
+    "Isa",
+    "Is",
+    "Jer",
+    "Je",
+    "Jr",
+    "Lam",
+    "La",
+    "Ezek",
+    "Eze",
+    "Ezk",
+    "Dan",
+    "Da",
+    "Dn",
+    "Hos",
+    "Ho",
+    "Joel",
+    "Joe",
+    "Jl",
+    "Amos",
+    "Am",
+    "Obad",
+    "Ob",
+    "Jnh",
+    "Jon",
+    "Micah",
+    "Mic",
+    "Nah",
+    "Na",
+    "Hab",
+    "Zeph",
+    "Zep",
+    "Zp",
+    "Haggai",
+    "Hag",
+    "Hg",
+    "Zech",
+    "Zec",
+    "Zc",
+    "Mal",
+    "Mal",
+    "Ml",
+    "Matt",
+    "Mt",
+    "Mrk",
+    "Mk",
+    "Mr",
+    "Luk",
+    "Lk",
+    "John",
+    "Jn",
+    "Jhn",
+    "Acts",
+    "Ac",
+    "Rom",
+    "Ro",
+    "Rm",
+    "Co",
+    "Cor",
+    "Corinthians",
+    "Gal",
+    "Ga",
+    "Ephes",
+    "Eph",
+    "Phil",
+    "Php",
+    "Col",
+    "Col",
+    "Th",
+    "Thes",
+    "Thess",
+    "Thessalonians",
+    "Ti",
+    "Tim",
+    "Timothy",
+    "Titus",
+    "Tit",
+    "Philem",
+    "Phm",
+    "Hebrews",
+    "Heb",
+    "He",
+    "James",
+    "Jas",
+    "Jm",
+    "Pe",
+    "Pet",
+    "Pt",
+    "Peter",
+    "Jn",
+    "Jo",
+    "Joh",
+    "Jhn",
+    "John",
+    "Jude",
+    "Jd",
+    "Jud",
+    "Jud",
+    "Rev",
+    "The Revelation",
+    "Genesis",
+    "Exodus",
+    "Leviticus",
+    "Numbers",
+    "Deuteronomy",
+    "Joshua",
+    "Judges",
+    "Ruth",
+    "Samuel",
+    "Kings",
+    "Chronicles",
+    "Ezra",
+    "Nehemiah",
+    "Esther",
+    "Job",
+    "Psalms",
+    "Psalm",
+    "Proverbs",
+    "Ecclesiastes",
+    "Song of Solomon",
+    "Isaiah",
+    "Jeremiah",
+    "Lamentations",
+    "Ezekiel",
+    "Daniel",
+    "Hosea",
+    "Joel",
+    "Amos",
+    "Obadiah",
+    "Jonah",
+    "Micah",
+    "Nahum",
+    "Habakkuk",
+    "Zephaniah",
+    "Haggai",
+    "Zechariah",
+    "Malachi",
+    "Matthew",
+    "Mark",
+    "Luke",
+    "John",
+    "Acts",
+    "Romans",
+    "Corinthians",
+    "Galatians",
+    "Ephesians",
+    "Philippians",
+    "Colossians",
+    "Thessalonians",
+    "Timothy",
+    "Titus",
+    "Philemon",
+    "Hebrews",
+    "James",
+    "Peter",
+    "John",
+    "Revelation",
+    "Re",
+    "Ap",
+    "Jd.",
+    "Heb.",
+]
+
+const preStrings = ["III", "II", "I", "1st", "2nd", "3rd", "First", "Second", "Third", "1", "2", "3"]
+const preStringed = [
+    "Sam",
+    "Samuel",
+    "Kings",
+    "Kgs",
+    "Kin",
+    "Chron",
+    "Chronicles",
+    "Corinthians",
+    "Co",
+    "Cor",
+    "Thessalonians",
+    "Th",
+    "Thes",
+    "Thess",
+    "Timothy",
+    "Ti",
+    "Tim",
+    "Peter",
+    "Pe",
+    "Pet",
+    "Pt",
+    "John",
+    "Jn",
+    "Jhn",
+]
+let text = `Joel 10:13 The passages Luke 2:32 and Lk 1:23 that we are looking at tonight 1 Cor 12:34 2 Cor 3:4 are found Jude 6, in Jude 5, Genesis 2:1 - 3:19, 1 John 3:16-17, 1 Peter 1:1, and Romans 10:13, 15, 17. Please turn in your Bibles. Ps 109:4,5,6,8.  Isaiah 61.2-3 Mt 5.4
+
+Ge 27.27-29,89-40 Heb 11.20 Heb. 12.17 Jonah 3
+
+Jd. 5
+Jd 6
+
+1 Cor 12:34 2 Cor 3:4. He 4.12 Re 1.16
+
+Leviticus 16:6 He 5.3 He 7.27
+
+Hos 10:1-3, 8 and 1 John 2:23`
+//add the prestringed versions e.g. 1 Peter
+for (let b = 0; b < preStringed.length; b++) {
+    for (let pre = 0; pre < preStrings.length; pre++) {
+        books.push(preStrings[pre] + " " + preStringed[b])
+    }
+}
+// add the book name with . at the end as this seems to be added sometimes, at least to the shortened forms
+const length = books.length
+for (let b = 0; b < length; b++) {
+    books.push(books[b] + ".")
+}
+
+// sort descending - longer items first
+books.sort((a, b) => b.length - a.length)
+let booksAt = []
+// go thro' each book finding where it matches in text
+for (let b = 0; b < books.length; b++) {
+    const book = books[b]
+    let chNoInText = 0
+    while (chNoInText < text.length) {
+        let j = text.indexOf(book, chNoInText)
+        if (j < 0) break
+        if (j + book.length < text.length && !text.charAt(j + book.length).match(/^[a-z]+$/)) {
+            booksAt.push([book, j])
+            let replacement = book
+            for (let k = 0; k < book.length; k++) {
+                replacement = replacement.replace(book.charAt(k), "X")
+            }
+            text = text.replace(book, replacement) // to prevent a shorter version matching
+        }
+        chNoInText = j + book.length + 1
+    }
+}
+// into ascending order of start position
+booksAt.sort(function (a, b) {
+    return a[1] - b[1]
+})
+newText = ""
+let chNoInText = 0
+for (let b = 0; b < booksAt.length; b++) {
+    while (chNoInText < booksAt[b][1]) {
+        //copy across characters to start of book
+        newText += text.charAt(chNoInText)
+        chNoInText++
+    }
+    newText += "<span>" + booksAt[b][0] + "</span><span>"
+    chNoInText += booksAt[b][0].length //skip the 'fill-in characters
+    for (let i = 0; i < 100; i++) {
+        chNoInText++
+        const nextCh = text.charAt(chNoInText)
+        //test whether are at the end of the chapter(s) and verse(s)
+        if (nextCh.match(/^[a-z]+$/)) break
+        if (nextCh.match(/^[A-Z]+$/)) break
+        newText += text.charAt(chNoInText - 1)
+    }
+    newText += "</span>&nbsp;"
+}
+document.querySelector("div").innerHTML = newText

package/src/CodexParser.js

@@ -27,21 +27,31 @@ class CodexParser {
      * @return {array} The found passages from the text.
      */
     scan(text) {
-        const abbrs = text.match(/(?:He)(?=.\d+)/gm)
-        if (abbrs) {
-            const matches = abbrs.map((string) => {
-                return {
-                    abbr: string,
-                    book: this.bookify(string),
-                }
+        const regex = /(?:He(?=\s?\d+))/g
+        let match
+        const matches = []
+
+        while ((match = regex.exec(text)) !== null) {
+            const index = match.index
+            const book = this.bookify(match[0])
+            matches.push({
+                abbr: match[0],
+                book: book,
+                index: index,
             })
-            for (let i = 0; i < matches.length; i++) {
-                const match = matches[i]
-                text = text.replace(match.abbr, match.book)
-            }
+        }
+        for (let i = matches.length - 1; i >= 0; i--) {
+            const match = matches[i]
+            text = text.substring(0, match.index) + match.book + text.substring(match.index + match.abbr.length)
         }
         const passages = this.crawler.parse(text).parsed_entities()
-        this.found.push(...passages.flatMap((passage) => passage.entities))
+        for (let j = 0; j < passages.length; j++) {
+            const passage = passages[j]
+            for (let i = 0; i < passage.entities.length; i++) {
+                const entity = passage.entities[i]
+                this.found.push(entity)
+            }
+        }
     }
 
     /**
@@ -51,8 +61,9 @@ class CodexParser {
      * @return {array} An array of parsed passages.
      */
     parse(reference) {
+        //TODO: Need to fix chapter ranges when another verse is tacted onto the end of it.
         if (!reference) {
-            throw new Error("Parse error (parse(), line 46): reference is undefined")
+            throw new Error("Parse error (parse(): reference is undefined")
         }
         this.passages = []
         this.scan(reference)
@@ -70,6 +81,10 @@ class CodexParser {
         //console.log(booksWithResults)
         for (let i = 0; i < booksWithResults.length; i++) {
             const initialPassage = booksWithResults[i].shift()
+            const shouldBeRange = initialPassage.osis.match(/[-–—]/)
+            if(shouldBeRange) {
+                initialPassage.type = "range"
+            }
             const firstPassage = {
                 original: initialPassage.osis,
                 book: this.bookify(initialPassage.start.b),
@@ -151,50 +166,6 @@ class CodexParser {
         }
         this.found = []
         return this
-        //console.log(booksWithResults)
-        /* for (let i = 0; i < this.found.length; i++) {
-            const hasChapterRange = this.found[i].match(/(?<=-\s?)\b\d+[.:].+\b/)
-            const book = this.found[i].match(this.bookRegex)
-            if (book === null) continue
-            let verse,
-                chapter = this.found[i].replace(book[0], "").match(this.chapterRegex)
-            if (this.found[i].match(this.verseRegex))
-                verse = this.found[i].match(this.verseRegex)[0].replace(/[:.]/, "").trim()
-            else {
-                if (this.bookify(book).toLowerCase() === "jude" || this.bookify(book).toLowerCase() === "philemon") {
-                    verse = chapter
-                    chapter = "1"
-                } else {
-                    verse = []
-                }
-            }
-            const passage = {
-                original: this.found[i].replace(/([.,])\1*$/, "").trim(),
-                book: this.bookify(book),
-                chapter: this.chapterify(chapter),
-                verses: verse,
-            }
-
-            if (hasChapterRange) {
-                passage.to = {
-                    book: passage.book,
-                    chapter: this.chapterify(hasChapterRange[0].match(this.chapterRegex)),
-                    verses: hasChapterRange[0].match(this.verseRegex)[0].replace(/[:.]/, "").trim(),
-                }
-                passage.to.verses = passage.to.verses.split(/,/).filter(Boolean)
-                passage.to.testament = this.bible.old.includes(passage.to.book) ? "old" : "new"
-            }
-            passage.verses =
-                typeof passage.verses !== "object"
-                    ? passage.verses.split(/,/).filter(Boolean)
-                    : passage.verses.filter((item) => item.trim())
-            passage.testament = this.bible.old.includes(passage.book) ? "old" : "new"
-            passage.scripture = this.scripturize(passage)
-            this.passages.push(passage)
-        }
-
-        this.found = []
-        return this.passages */
     }
     chapterify(chapter) {
         if (chapter.type === "range") {

package/src/regex.js

@@ -4,7 +4,7 @@ const verseRegex =  /\b[:.].+\b/gm
 const chapterRange = /.?\s?(?:[-—–])\s?/gm
 const chapterRangeVerseRegex = /(?:.\d+)?/gm
 const chapterVerseRange =
-    /.?(?:\d+)((?:[:.])(?:(\d+)?)(?:(,\s?\d+)*)?(?:\s?[-–—]\s?\d+)?(?:,\s?\d+(?:\s?[-–—]\s?\d+)?)?(?:[:.]\d+)?)?/gim
+    /.?\s?(?:\d+[:.])?\d+[a-e]?(?:(?:\s?[-–—]|,)(?!\s[1-3]\s+[A-Z])\s?(?:\d+[:.])?\d+[a-e]?)*/gim
 const scripturesRegex = new RegExp(`(${bookRegex.source})(${chapterVerseRange.source})`, "gmi")
 module.exports.bookRegex = bookRegex
 module.exports.chapterRegex = chapterRegex

package/sub-verse-scripture-test.js

@@ -1,6 +1,5 @@
-const CodexParser = require("./src/CodexParser.js")
-
-const parser = new CodexParser()
-const scripture = "And then he said, turn to He 1:1-3, 8. and He doesn't like it"
-const result = parser.parse(`${scripture}. Please turn in your Bibles.`)
+const BibleParser = require("./src/CodexParser.js")
+const string = "Ps 109:4,5,6,8"
+const parser = new BibleParser()
+const result = parser.parse(string)
 console.log(result.getPassages())