codexparser 0.1.4 → 0.1.6

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "codexparser",
-  "version": "0.1.4",
+  "version": "0.1.6",
   "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/src/CodexParser.js

@@ -96,6 +96,12 @@ class CodexParser {
             return false
         }
 
+        // Function to detect suffixes like "LXX" or "MT"
+        const detectSuffix = (startIndex) => {
+            const suffixMatch = text.substring(startIndex).match(/\b(LXX|MT)\b/i)
+            return suffixMatch ? suffixMatch[0].toUpperCase() : null
+        }
+
         // Loop through the text and check for full names and abbreviations
         while (i < lowerCaseText.length) {
             let foundBook = null
@@ -128,20 +134,30 @@ class CodexParser {
                             isBoundaryOrNonAlphabetic(i - 1, lowerCaseText) &&
                             isBoundaryOrNonAlphabetic(i + abbreviationWithDot.length, lowerCaseText)
                         ) {
-                            foundBook = abbreviations[k] // Store the abbreviation without the dot
-                            foundIndex = i // Record the index where the abbreviation is found
-                            matchedLength = abbreviationWithDot.length // Update the length of the match to include the dot
-                            break // Exit once found
+                            // Look ahead to check if a number or space + number follows the abbreviation
+                            const afterAbbreviation = lowerCaseText.substring(i + abbreviationWithDot.length).trim()
+                            if (/^\d+/.test(afterAbbreviation)) {
+                                // Check if there is a number (chapter/verse)
+                                foundBook = abbreviations[k] // Store the abbreviation without the dot
+                                foundIndex = i // Record the index where the abbreviation is found
+                                matchedLength = abbreviationWithDot.length // Update the length of the match to include the dot
+                                break // Exit once found
+                            }
                         }
                     } else if (lowerCaseText.startsWith(abbreviation, i)) {
                         if (
                             isBoundaryOrNonAlphabetic(i - 1, lowerCaseText) &&
                             isBoundaryOrNonAlphabetic(i + abbreviation.length, lowerCaseText)
                         ) {
-                            if (abbreviation.length > matchedLength) {
-                                foundBook = abbreviations[k] // Store the abbreviation without the dot
-                                foundIndex = i // Record the index where the abbreviation is found
-                                matchedLength = abbreviation.length // Update the length of the match
+                            // Look ahead to check if a number or space + number follows the abbreviation
+                            const afterAbbreviation = lowerCaseText.substring(i + abbreviation.length).trim()
+                            if (/^\d+/.test(afterAbbreviation)) {
+                                // Check if there is a number (chapter/verse)
+                                if (abbreviation.length > matchedLength) {
+                                    foundBook = abbreviations[k] // Store the abbreviation without the dot
+                                    foundIndex = i // Record the index where the abbreviation is found
+                                    matchedLength = abbreviation.length // Update the length of the match
+                                }
                             }
                         }
                     }
@@ -170,17 +186,22 @@ class CodexParser {
                 // Replace any periods within the reference with colons for easier parsing
                 const formattedReference = chapterVerse.replace(/\./g, ":")
 
+                // Detect if a suffix (LXX or MT) exists after the chapter/verse
+                const suffix = detectSuffix(i)
+
                 if (formattedReference.length > 0) {
                     this.found.push({
                         book: foundBook,
-                        reference: formattedReference, // Store the formatted reference
+                        reference: formattedReference, // Store only the chapter/verse
                         index: foundIndex,
+                        version: suffix || null, // Store the version (LXX, MT) if found, otherwise null
                     })
                 } else {
                     this.found.push({
                         book: foundBook,
                         reference: null,
                         index: foundIndex,
+                        version: suffix || null, // Store the version (LXX, MT) if found, otherwise null
                     })
                 }
             } else {
@@ -196,7 +217,7 @@ class CodexParser {
 
         this.passages = this.found.map((passage) => {
             const book = this.bookify(passage.book)
-
+            dump(passage)
             // Initialize the parsed passage object
             const parsedPassage = {
                 original: passage.book + " " + passage.reference,
@@ -207,6 +228,7 @@ class CodexParser {
                 type: null, // Set type based on reference
                 testament: this.bible.old.find((bible) => bible === book) ? "old" : "new",
                 index: passage.index,
+                version: this._handleVersion(passage.version),
             }
 
             // Split reference by commas to handle multiple ranges or verses (e.g., "Ge 27:27-29,39-41")
@@ -445,6 +467,27 @@ class CodexParser {
                 },
             }
         }
+        return true
+    }
+    _handleVersion(version) {
+        if (!version) {
+            return null
+        }
+        if (version.toLowerCase() === "lxx") {
+            return {
+                name: "Septuagint",
+                value: "LXX",
+                abbreviation: "lxx",
+            }
+        }
+
+        if (version.toLowerCase() === "mt") {
+            return {
+                name: "Masoretic Text",
+                value: "MT",
+                abbreviation: "mt",
+            }
+        }
     }
 }