usfm-grammar-web 3.0.0-beta.15 → 3.0.0-beta.17

package/README.md

@@ -23,10 +23,10 @@ function App() {
 
   useEffect(() => {
     const initParser = async () => {
-      await USFMParser.init("https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.15/tree-sitter-usfm.wasm",
-                            "https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.15/tree-sitter.wasm");
-      await Validator.init("https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.15/tree-sitter-usfm.wasm",
-                            "https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.15/tree-sitter.wasm");
+      await USFMParser.init("https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.17/tree-sitter-usfm.wasm",
+                            "https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.17/tree-sitter.wasm");
+      await Validator.init("https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.17/tree-sitter-usfm.wasm",
+                            "https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.17/tree-sitter.wasm");
 
     };
     initParser();
@@ -60,13 +60,13 @@ It can be used directly in the HTML script tag too. Please ensure its dependenci
 
 ```html
 <script type="module">
-  import { USFMParser, Filter, Validator } from 'https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.15/dist/bundle.mjs';
+  import { USFMParser, Filter, Validator } from 'https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.17/dist/bundle.mjs';
   console.log('Hello world');
   (async () => {
-  await USFMParser.init("https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.15/tree-sitter-usfm.wasm",
-                            "https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.15/tree-sitter.wasm");
-  await Validator.init("https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.15/tree-sitter-usfm.wasm",
-                            "https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.15/tree-sitter.wasm");
+  await USFMParser.init("https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.17/tree-sitter-usfm.wasm",
+                            "https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.17/tree-sitter.wasm");
+  await Validator.init("https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.17/tree-sitter-usfm.wasm",
+                            "https://cdn.jsdelivr.net/npm/usfm-grammar-web@3.0.0-beta.17/tree-sitter.wasm");
   const usfmParser = new USFMParser('\\id GEN\n\\c 1\n\\p\n\\v 1 In the begining..\\v 2 more text')
   const output = usfmParser.toUSJ()
   console.log({ output })
@@ -124,6 +124,34 @@ const usfmParser2 = new USFMParser(usfmString=null, fromUsj=null, fromUsx=usxEle
 const usfmGen = usfmParser2.usfm;
 console.log(usfmGen);
 ```
+### BibleNLP format
+Bible NLP format consists of two `txt` files: the first, with verse texts, one per line and the second, with corresponding references. The API generates a JSON with two fields, `text` and `vref`, each containing an array of strings.
+
+```javascript
+
+const output = usfmParser.toBibleNlpFormat() 
+//const output = my_parser.toBibleNlpFormat(true) //ignore_errors
+
+const textLines = output.text.join('\n');
+fs.writeFileSync('bibleNLP.txt', textLines, { encoding: 'utf-8' });
+
+const refLines = output.vref.join('\n');
+fs.writeFileSync('vref.txt', refLines, { encoding: 'utf-8' });
+```
+
+### Table/List format
+
+```javascript
+const listOutput = usfmParser.toList();
+/* const listOutput = usfmParser.toList(
+                      Filter.NOTES,  //exclude
+                      ["id", "c", "v"] //include
+                      true,  //ignore errors
+                      true  //combine texts
+                      )*/
+const tableOutput = listOutput.map(row => row.join('\t')).join('\n');
+console.log(tableOutput);
+```
 
 ### Autofix and Validation
 Experimental Validation and Autofix feature for USFM:
@@ -193,9 +221,9 @@ The filtering on USJ, the JSON output, is a feature incorporated to allow data e
     ```
     To inspect which are the markers in each of these options, it could be just printed out, `print(Filter.TITLES)`. These could be used individually or concatinated to get the desired filtering of markers and data:
     ```javascript
-    output = usfmParser.toUSJ(null, include_markers=Filter.BCV)
-    output = usfmParser.toUSJ(null, include_markers=Filter.BCV+Filter.TEXT)
-    output = usfmParser.toUSJ(exclude_markers=Filter.PARAGRAPHS+Filter.CHARACTERS)
+    output = usfmParser.toUSJ(null, Filter.BCV) //to include
+    output = usfmParser.toUSJ(null, [...Filter.BCV, ...Filter.TEXT]) //to include
+    output = usfmParser.toUSJ([...Filter.PARAGRAPHS, ...Filter.CHARACTERS]) //to exclude
     ``` 
 - Inner contents of excluded markers
 

package/dist/bundle.mjs

@@ -1660,7 +1660,8 @@ const $142605215cbb4f88$export$b32929182cc4fefe = [
 const $142605215cbb4f88$export$75b2f422ff60acaf = [
     "char",
     "note",
-    "figure"
+    "figure",
+    "ref"
 ];
 const $142605215cbb4f88$export$aa24f570494ce8d0 = [
     "type",
@@ -1707,6 +1708,16 @@ class $ce44dcc4919407eb$var$USFMGenerator {
         this.usfmString = "";
     }
     usjToUsfm(usjObj, nested = false) {
+        if (usjObj.type === 'optbreak') {
+            if (this.usfmString !== '' && ![
+                '\n',
+                '\r',
+                ' ',
+                '\t'
+            ].includes(this.usfmString.slice(-1))) this.usfmString += ' ';
+            this.usfmString += '// ';
+            return;
+        }
         if (usjObj.type === "ref") usjObj.marker = "ref";
         if (!(0, $142605215cbb4f88$export$b32929182cc4fefe).includes(usjObj.type)) {
             this.usfmString += "\\";
@@ -1731,11 +1742,15 @@ class $ce44dcc4919407eb$var$USFMGenerator {
         }
         if (Array.isArray(usjObj.content)) usjObj.content.forEach((item)=>{
             if (typeof item === "string") this.usfmString += item;
-            else this.usjToUsfm(item, usjObj.type === "char");
+            else this.usjToUsfm(item, usjObj.type === "char" && item.marker !== "fv");
         });
         let attributes = [];
         Object.keys(usjObj).forEach((key)=>{
-            if (!(0, $142605215cbb4f88$export$aa24f570494ce8d0).includes(key)) attributes.push(`${key}="${usjObj[key]}"`);
+            if (!(0, $142605215cbb4f88$export$aa24f570494ce8d0).includes(key)) {
+                let lhs = key;
+                if (key === "file") lhs = "src";
+                attributes.push(`${lhs}="${usjObj[key]}"`);
+            }
         });
         if (attributes.length > 0) this.usfmString += `|${attributes.join(" ")}`;
         if ((0, $142605215cbb4f88$export$75b2f422ff60acaf).includes(usjObj.type)) {
@@ -1743,6 +1758,14 @@ class $ce44dcc4919407eb$var$USFMGenerator {
             if (nested && usjObj.type === "char") this.usfmString += "+";
             this.usfmString += `${usjObj.marker}* `;
         }
+        if (usjObj.type === "ms") {
+            if ("sid" in usjObj) {
+                if (attributes.length == 0) this.usfmString += '|';
+                this.usfmString += `sid="${usjObj.sid}" `;
+            }
+            this.usfmString = this.usfmString.trim() + "\\*";
+        }
+        if (usjObj.type === "sidebar") this.usfmString += "\\esbe";
         if (!(0, $142605215cbb4f88$export$c63c0b6e358f0774).includes(usjObj.type) && this.usfmString[this.usfmString.length - 1] !== "\n") this.usfmString += "\n";
         return this.usfmString;
     }
@@ -2395,6 +2418,12 @@ class $0143e94dfd2d689d$var$ListGenerator {
                 "Marker"
             ]
         ];
+        this.bibleNlpFormat = {
+            "text": [],
+            "vref": []
+        };
+        this.prevChapter = "";
+        this.prevVerse = "";
     }
     usjToListId(obj) {
         /* Update book code */ this.book = obj.code;
@@ -2425,6 +2454,24 @@ class $0143e94dfd2d689d$var$ListGenerator {
             else this.usjToList(item);
         }
     }
+    usjToBibleNlpFormat(obj) {
+        // Traverse the USJ object and build a dictionary for Bible NLP format
+        if (obj.type === "book") this.usjToListId(obj);
+        else if (obj.type === "chapter") this.usjToListC(obj);
+        else if (obj.type === "verse") this.usjToListV(obj);
+        else if (obj.content) {
+            for (const item of obj.content)if (typeof item === "string") {
+                if (this.currentChapter === this.prevChapter && this.currentVerse === this.prevVerse) this.bibleNlpFormat.text[this.bibleNlpFormat.text.length - 1] += " " + item.replace(/[\n\r]/g, " ").trim();
+                else {
+                    const vref = `${this.book} ${this.currentChapter}:${this.currentVerse}`;
+                    this.bibleNlpFormat.text.push(item.replace(/[\n\r]/g, " ").trim());
+                    this.bibleNlpFormat.vref.push(vref);
+                    this.prevChapter = this.currentChapter;
+                    this.prevVerse = this.currentVerse;
+                }
+            } else this.usjToBibleNlpFormat(item);
+        }
+    }
 }
 var $0143e94dfd2d689d$export$2e2bcd8739ae039 = $0143e94dfd2d689d$var$ListGenerator;
 
@@ -3320,6 +3367,31 @@ Only one of USFM, USJ or USX is supported in one object.`);
             });
         }
     }
+    toBibleNlpFormat(ignoreErrors = false) {
+        /* Uses the toUSJ function with only BVC and text.
+	       Then the JSOn is converted to list of verse texts and vrefs*/ if (!ignoreErrors && this.errors.length > 0) {
+            let errorString = this.errors.join("\n\t");
+            throw new Error(`Errors present:\n\t${errorString}\nUse ignoreErrors=true to generate output despite errors`);
+        }
+        try {
+            const usjDict = this.toUSJ(null, [
+                ...(0, $ab5c81e737a0c6a6$export$ec91da630f36d5ea).BCV,
+                ...(0, $ab5c81e737a0c6a6$export$ec91da630f36d5ea).TEXT
+            ], ignoreErrors, true);
+            const listGenerator = new (0, $0143e94dfd2d689d$export$2e2bcd8739ae039)();
+            listGenerator.usjToBibleNlpFormat(usjDict);
+            return listGenerator.bibleNlpFormat;
+        } catch (exe) {
+            let message = "Unable to do the conversion. ";
+            if (this.errors.length > 0) {
+                let errorString = this.errors.join("\n\t");
+                message += `Could be due to an error in the USFM\n\t${errorString}`;
+            }
+            throw new Error(message, {
+                cause: exe
+            });
+        }
+    }
     toUSX(ignoreErrors = false) {
         /* Convert the syntax_tree to the XML format (USX) */ if (!ignoreErrors && this.errors.length > 0) {
             let errorString = this.errors.join("\n\t");
@@ -3572,6 +3644,13 @@ class $882b1daec90c4038$export$9eeb22c0bba4ed5e {
                 const toReplace = modifiedUSFM.slice(start, end);
                 modifiedUSFM = modifiedUSFM.replace(toReplace, `${toReplace}\\p\n`);
                 changed = true;
+            } else if (error.isError && !errorText.startsWith("\\") && error.previousSibling.type === "chapter" && !error.children.some((ch)=>ch.type === "paragraph")) {
+                // console.log("Match 7.1");
+                const start = error.previousSibling.startIndex;
+                const end = error.startIndex;
+                const toReplace = modifiedUSFM.slice(start, end);
+                modifiedUSFM = modifiedUSFM.replace(toReplace, `${toReplace}\\p\n`);
+                changed = true;
             } else if (errorText.startsWith("\\") && !$882b1daec90c4038$var$validMarkersPattern.test(errorText)) {
                 // console.log("Match 8");
                 modifiedUSFM = modifiedUSFM.replace(errorText, errorText.slice(1));