codexparser 0.0.79 → 0.0.81

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "codexparser",
-  "version": "0.0.79",
+  "version": "0.0.81",
   "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": {

package/scan-test.js

@@ -4,20 +4,7 @@ const util = require("util")
 const dump = (item) => {
     console.log(util.inspect(item, { depth: null, colors: true }))
 }
-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
-
-exod15.18. 2 Cor 12:23 Malachi 3:32`
+let text = `Psalm 94:4-100:6 MT`
 const parser = new BibleParser()
-const result = parser.find(text)
+const result = parser.find(text).enhance()
 dump(result)

package/src/CodexParser.js

@@ -22,6 +22,35 @@ class CodexParser {
         this.EzraAbbrv = EzraAbbrv
         //this.toc = toc
         this.crawler = new crawler()
+        this.preStrings = ["III", "II", "I", "1st", "2nd", "3rd", "First", "Second", "Third", "1", "2", "3"]
+        this.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",
+        ]
+
+        this.text = String
     }
 
     /**
@@ -90,6 +119,7 @@ class CodexParser {
         }
         this.passages = []
         this.scan(reference)
+        const books = []
         for (let i = 0; i < this.found.length; i++) {
             const result = this.found[i]
             if (result.type === "range" && result.start.b !== result.end.b) {
@@ -138,13 +168,14 @@ class CodexParser {
             }
             passage.original = result.osis
             passage.scripture = this.scripturize(passage)
+            passage.passages = this.populate(result.entities[0], passage.verses)
             passage.indices = result.indices
-            passage.entities = result.entities
-            if (passage.entities[0].translations) {
+            passage.entities = result.entities[0]
+            if (passage.entities.translations) {
                 passage.version = {
-                    name: passage.entities[0].translations[0].translation,
-                    alias: passage.entities[0].translations[0].alias,
-                    abbreviation: passage.entities[0].translations[0].osis,
+                    name: passage.entities.translations[0].translation,
+                    alias: passage.entities.translations[0].alias,
+                    abbreviation: passage.entities.translations[0].osis,
                 }
             }
             this.passages.push(passage)
@@ -152,6 +183,37 @@ class CodexParser {
         this.found = []
         return this
     }
+
+    populate(entities, verses) {
+        let passages = []
+        for (let i = entities.start.v; i <= entities.end.v; i++) {
+            passages.push({
+                book: entities.start.b,
+                chapter: entities.start.c,
+                verse: i,
+            })
+        }
+
+        if (verses.length > 1) {
+            for (let i = 0; i < verses.length; i++) {
+                const passage = {
+                    book: entities.start.b,
+                    chapter: entities.start.c,
+                    verse: verses[i],
+                }
+                if (
+                    !passages.find(
+                        (p) => p.book === passage.book && p.chapter === passage.chapter && p.verse === passage.verse
+                    )
+                ) {
+                    passages.push(passage)
+                }
+            }
+        }
+
+        return [...new Set(passages)]
+    }
+
     chapterify(chapter) {
         return chapter.start.c
     }
@@ -229,262 +291,18 @@ class CodexParser {
         return parts
             .join(" ")
             .replace(/\s+:\s+/g, ":")
+            .replace(/\s[-–—]\s/, "-")
             .trim()
     }
     find(text) {
-        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 books = [...Object.keys(this.abbrevations), ...this.bible.new, ...this.bible.old]
 
-        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 newText = ""
 
         //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])
+        for (let b = 0; b < this.preStringed.length; b++) {
+            for (let pre = 0; pre < this.preStrings.length; pre++) {
+                books.push(this.preStrings[pre] + " " + this.preStringed[b])
             }
         }
         // add the book name with . at the end as this seems to be added sometimes, at least to the shortened forms
@@ -529,29 +347,67 @@ class CodexParser {
             newText += "<span class='passage'>" + booksAt[b][0]
             let passage = booksAt[b][0]
             chNoInText += booksAt[b][0].length //skip the 'fill-in characters
+            let abbr
+            let index = []
             for (let i = 0; i < 100; i++) {
                 chNoInText++
-                const nextCh = text.charAt(chNoInText)
+                let nextCh = text.charAt(chNoInText)
+                const testStr = text.substring(chNoInText - passage.length, chNoInText + 5).toLowerCase()
+                if (testStr.includes("lxx")) abbr = "lxx"
+                if (testStr.includes("na")) abbr = "na"
+                if (testStr.includes("ubs")) abbr = "ubs"
+                if (testStr.includes("mt")) abbr = "mt"
+                if (testStr.includes("bhs")) abbr = "bhs"
+                if (testStr.includes("lxx")) abbr = "lxx"
+                if (testStr.includes("na")) abbr = "na"
+                if (testStr.includes("ubs")) abbr = "ubs"
+                if (testStr.includes("mt")) abbr = "mt"
+                if (testStr.includes("bhs")) abbr = "bhs"
                 //test whether are at the end of the chapter(s) and verse(s)
-                if (nextCh.match(/^[a-z]+$/) && nextCh !== "f" && nextCh !== "ff") break
+                if (nextCh.match(/^[a-z]+$/) && nextCh !== "f" && nextCh !== "ff" && nextCh !== "a") break
                 if (nextCh.match(/^[A-Z]+$/)) break
                 newText += text.charAt(chNoInText - 1)
                 passage += text.charAt(chNoInText - 1)
+                index.push(chNoInText - 1)
             }
-            this.found.push(passage.trim())
+
+            index = [index[0], index[index.length - 1]]
+            console.log(index)
+            this.found.push(passage.trim() + (abbr ? " " + abbr.toUpperCase() : ""))
             newText += "</span>&nbsp;"
         }
+        this.text = newText
         return this
     }
 
+    getText() {
+        return this.text
+    }
+
     enhance() {
         if (this.found.length > 0) {
             for (let i = 0; i < this.found.length; i++) {
+                const found = this.found[i]
+                const book = this.bookify(this.found[i].match(this.bookRegex)[0])
+                const passageWithoutBook = found.replace(book, "")
+                let chapter, verse
+                if (/[:\.]/.test(passageWithoutBook)) {
+                    chapter = parseInt(passageWithoutBook.split(":").shift().trim(), 10)
+                    verse = parseInt(passageWithoutBook.split(":").pop().trim(), 10)
+                } else {
+                    if (/\d+/gim.test(passageWithoutBook)) {
+                        chapter = parseInt(passageWithoutBook.trim())
+                        verse = null
+                    }
+                }
+
+                let type = "verseRange"
+
                 const passage = {
                     original: this.found[i],
                     book: this.bookify(this.found[i].match(this.bookRegex)[0]),
                     chapter: this.found[i].match(this.chapterRegex),
-                    verse: this.found[i].match(/(?<=[.:])(\d+.+)/),
+                    verse: this.found[i].match(/(?<=[.:])(\d+.+)/)[0],
                 }
                 this.passages.push(passage)
             }

package/src/abbr.js

@@ -91,7 +91,6 @@ const abbrevations = {
     "II Ch": "2 Chronicles",
     Ezra: "Ezra",
     Ezr: "Ezra",
-    Ez: "Ezra",
     Neh: "Nehemiah",
     Ne: "Nehemiah",
     Esth: "Esther",

package/src/functions.js

@@ -0,0 +1,6 @@
+const util = require("util")
+const dump = (item) => {
+    console.log(util.inspect(item, { depth: null, colors: true }))
+}
+
+module.exports.dump = dump

package/sub-verse-scripture-test.js

@@ -10,6 +10,7 @@ parser.options({
     invalid_passage_strategy: "include",
     invalid_sequence_strategy: "include",
     single_chapter_1_strategy: "verse",
+    sequence_combination_strategy: "combine",
 })
-const result = parser.parse("Isaiah 8:21-9:6")
+const result = parser.parse("Jude 5-7,11 Numbers 14:29-30 Genesis 19:24-25 Genesis 4:3-8 Numbers 31:16 Numbers 16:1-50")
 dump(result.getPassages())

package/tests/abbreviated_verses.js

@@ -0,0 +1,8 @@
+const BibleParser = require("../src/CodexParser.js")
+const dump = require("../src/functions.js").dump
+const parser = new BibleParser()
+const text = "Job 1:1b"
+
+const passages = parser.find(text).enhance()
+
+dump(passages)

package/{bcv-single-test.js → tests/bcv-single-test.js}

@@ -4,11 +4,12 @@ const util = require("util")
 const dump = (item) => {
     console.log(util.inspect(item, { depth: null, colors: true }))
 }
-const text = "Psalm 34:12f"
+const text = "John 12:38 John 1:29,34 Isaiah 53:1 Isaiah 6:10 Isaiah 6:1 Isaiah 52:13 Isaiah 6:3 LXX Isaiah 52:13 LXX Isaiah 6:7 Isaiah 53:12 Isaiah 52:13 - 53:12"
 
 const parser = new bcv_parser({
     invalid_sequence_strategy: "include",
     invalid_passage_strategy: "include",
+    sequence_combination_strategy: "combine"
 })
 const textParser = parser.parse(text)
 console.log(textParser)

package/tests/find.js

@@ -0,0 +1,8 @@
+const CodexParser = require("../src/CodexParser.js")
+
+const parser = new CodexParser()
+
+parser.find('Psalm 2:2-13; 3:2-4 30:5 LXX').enhance()
+
+console.log(parser.getPassages())
+console.log(parser.getText())

package/tests/single.js

@@ -0,0 +1,10 @@
+const BibleParser = require("../src/CodexParser.js")
+const dump = require("../src/functions.js").dump
+
+const parser = new BibleParser()
+
+const text = "Job 1:1-5"
+
+const passages = parser.parse(text).getPassages()
+
+dump(passages)