Alpha.10 and beta.15

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 3.0.0-beta.14
+current_version = 3.0.0-beta.15
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)\-(?P<release>\w+).(?P<num>\d+)
@@ -37,3 +37,13 @@ replace = "version": "{new_version}"
 [bumpversion:file:tree-sitter-usfm3/package-lock.json]
 search = "version": "{current_version}"
 replace = "version": "{new_version}"
+
+[bumpversion:file:node-usfm-parser/package.json]
+
+[bumpversion:file:web-usfm-parser/package.json]
+search = "version": "{current_version}"
+replace = "version": "{new_version}"
+
+[bumpversion:file:web-usfm-parser/README.md]
+search = npm/usfm-grammar-web@{current_version}
+replace = npm/usfm-grammar-web@{new_version}

.github/workflows/check-on-push.yml

@@ -84,7 +84,7 @@ jobs:
         uses: actions/setup-node@v4
         with:
           node-version: 20
-      - name: Run tests
+      - name: Build grammar
         run: |
           cd tree-sitter-usfm3
           npm install --save nan
@@ -93,8 +93,12 @@ jobs:
       - name: Install dependencies
         run: |
           cd node-usfm-parser
+          sed -i '/"tree-sitter-usfm3":.*/d' package.json
           npm install .
           npm install ../tree-sitter-usfm3
+      - name: Run tests
+        run: |
+          cd node-usfm-parser
           node_modules/mocha/bin/mocha.js --timeout=40000 --grep "Include|Exclude|wild|Compare" --invert
 
   Run-Web-tests:
@@ -107,7 +111,7 @@ jobs:
         uses: actions/setup-node@v4
         with:
           node-version: 20
-      - name: Run tests
+      - name: Build grammar
         run: |
           cd tree-sitter-usfm3
           npm install --save nan
@@ -122,7 +126,9 @@ jobs:
           cp node_modules/web-tree-sitter/tree-sitter.js src/web-tree-sitter/
           cp node_modules/web-tree-sitter/tree-sitter.wasm ./
           cp ../tree-sitter-usfm3/tree-sitter-usfm3.wasm ./tree-sitter-usfm.wasm
-
+      - name: Run tests
+        run: |
+          cd web-usfm-parser
           node_modules/mocha/bin/mocha.js --timeout=40000 --grep "Include|Exclude|wild|Compare" --invert
 
 

.github/workflows/npm-publish.yml

@@ -49,3 +49,51 @@ jobs:
         env:
           NODE_AUTH_TOKEN: ${{secrets.npm_token}}
 
+  Publish-node-usfm-grammar:
+    needs: Test-grammar
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/setup-node@v1
+        with:
+          node-version: 20.4
+          registry-url: https://registry.npmjs.org/
+      - run: |
+          cd node-usfm-parser
+          sed -i '/"tree-sitter-usfm3":.*/d' package.json
+          npm install .
+          npm run build
+          npm publish . 
+        env:
+          NODE_AUTH_TOKEN: ${{secrets.npm_token}}
+
+  Publish-web-usfm-grammar:
+    needs: Test-grammar
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/setup-node@v1
+        with:
+          node-version: 20.4
+          registry-url: https://registry.npmjs.org/
+      - name: Build Grammar
+        run: |
+          cd tree-sitter-usfm3
+          npm install --save nan
+          npm install --save-dev tree-sitter-cli
+          ./node_modules/.bin/tree-sitter generate
+          ./node_modules/.bin/tree-sitter build --wasm
+          cp tree-sitter-usfm3.wasm ../web-usfm-parser/tree-sitter-usfm.wasm
+      - name: Install dependencies
+        run: |
+          cd web-usfm-parser/
+          npm install .
+          cp ./node_modules/web-tree-sitter/tree-sitter.js src/web-tree-sitter/
+          cp ./node_modules/web-tree-sitter/tree-sitter.wasm ./
+      - name: Build and publish
+        run: |
+          cd web-usfm-parser/
+          npm run build
+          npm publish .
+        env:
+          NODE_AUTH_TOKEN: ${{secrets.npm_token}}

docs/Dev_notes.md

@@ -49,6 +49,29 @@ pytest -k "not compare_usx_with_testsuite_samples and not testsuite_usx_with_rnc
 
 ```
 
+In node module:
+
+```bash
+cd node-usfm-parser
+npm run test
+
+# to run selectively
+node_modules/mocha/bin/mocha.js --timeout 40000 --grep "Compare" --bail
+node_modules/mocha/bin/mocha.js --timeout 40000 test/basic.js
+```
+
+In web module:
+
+```bash
+cd web-usfm-parser
+npm run test
+
+# to run selectively
+node_modules/mocha/bin/mocha.js --timeout 40000 --grep "Compare" --bail
+node_modules/mocha/bin/mocha.js --timeout 40000 test/basic.js
+```
+
+
 ## How to build and publish JS web module for local Development
 
 First compile the grammar and get the wasm file
@@ -57,7 +80,7 @@ cd tree-sitter-usfm3
 export PATH=$PATH:./node_modules/.bin
 tree-sitter generate
 tree-sitter build --wasm
-cp tree-sitter-usfm.wasm ../web-usfm-parser/
+cp tree-sitter-usfm3.wasm ../web-usfm-parser/tree-sitter-usfm.wasm
 cd ..
 ```
 After npm install, copy the `tree-sitter.js` file from `node_modules/web-tree-sitter` to the `js-usfm-parser/src/web-tree-sitter` folder to include it in the bundle. Also copy the `tree-sitter.wasm` file to `js-usfm-parser/` to be included in the npm packaging.
@@ -86,6 +109,8 @@ npm install -g verdaccio # need not do again if done once
 verdaccio # runs a server at localhost:4873
 touch .npmrc
 echo "registry=http://localhost:4873 # OR http://0.0.0.0:4873" > .npmrc
+rm -r .parcel-cache
+npm run build
 npm publish .
 ```
 

node-usfm-parser/README.md

@@ -11,19 +11,93 @@ npm install usfm-grammar
 ```
 
 ## Usage
-Here's how you can use USFM Grammar in your JavaScript/TypeScript projects:
+
+### Importing, parsing USFM, checking errors
 
 ```javascript
+const {USFMParser} = require('usfm-grammar');
+
+const USFM = '\\id GEN\n\\c 1\n\\p\n\\v 1 In the begining..\\v 2 some more text'
 const usfmParser = new USFMParser(USFM);
+console.log(usfmParser.errors)
+```
+
+### USJ 
+Here's how you can use USFM Grammar in your JavaScript projects to work with the JSON format, USJ:
+
+```javascript
+const {USFMParser} = require('usfm-grammar');
 
 const USFM = '\\id GEN\n\\c 1\n\\p\n\\v 1 In the begining..\\v 2 some more text'
-const USJ = usfmParser.toUSJ()
-console.log(USJ);
+const usfmParser = new USFMParser(USFM);
+
+const USJ = usfmParser.toUSJ() // USFM to USJ
+console.log(JSON.stringify(USJ, null, 2));
 
-const usfmParser2 = new USFMParser(usfmString=null, fromUsj=USJ)
+const usfmParser2 = new USFMParser(usfmString=null, fromUsj=USJ) // USJ to USFM
 const usfmGen = usfmParser2.usfm;
 console.log(usfmGen);
 ```
+Working with USJ, also gives options like filtering selected markers, to edit the original USFM content. To understand more about how `exclude_markers`, `include_markers`, `combine_texts`  and `Filter` works refer the section on [filtering on USJ](#filtering-on-usj)
+
+### USX
+
+To work with the XML format, USX:
+```javascript
+const {USFMParser} = require('usfm-grammar');
+const { DOMImplementation, XMLSerializer } = require('xmldom');
+
+const USFM = '\\id GEN\n\\c 1\n\\p\n\\v 1 In the begining..\\v 2 some more text'
+const usfmParser = new USFMParser(USFM);
+
+const usxElem = usfmParser.toUSX() // USFM to USX
+const usxSerializer = new XMLSerializer();
+const usx = usxSerializer.serializeToString(usxElem);
+
+console.log(usx);
+
+const usfmParser2 = new USFMParser(usfmString=null, fromUsj=null, fromUsx=usxElem) // USX to USFM
+const usfmGen = usfmParser2.usfm;
+console.log(usfmGen);
+```
+
+### Autofix and Validation
+Experimental Validation and Autofix feature for USFM:
+```javascript
+const {Validator} = require("usfm-grammar");
+
+const wrongUSFM="\\id GEN\n\\c 1\n\\v 1 test verse"
+const checker = new Validator();
+const resp = checker.isValidUSFM(wrongUSFM); // true or false
+console.log(checker.message) // List of errors if present
+
+const editedUSFM = checker.autoFixUSFM(wrongUSFM);
+console.log(checker.message); // Report on autofix attempt 
+
+```
+
+Validation of USJ format:
+```javascript
+const {Validator} = require("usfm-grammar");
+const simpleUSJ = {
+  type: 'USJ',
+  version: '0.3.0',
+  content: [
+    { type: 'book', marker: 'id', code: 'GEN', content: [] },
+    { type: 'chapter', marker: 'c', number: '1', sid: 'GEN 1' },
+    { type: 'para', marker: 'p', content: [
+        {type: 'verse', marker: 'v', number: 1 },
+        "In the begining..",
+        {type: 'verse', marker: 'v', number: 2 }
+      ] }
+  ]
+}
+const checker = new Validator();
+console.log(checker.isValidUSJ(simpleUSJ));
+console.log(checker.message);
+```
+
+### From ESM Project
 
 When using in an ESModule, if `import {USFMParser} from 'usfm-grammar` doesnt work for you, you could try:
 ```javascript
@@ -33,25 +107,53 @@ const {USFMParser} = pkg;
 ...
 ```
 
-## API Documentation
+### Filtering on USJ
+The filtering on USJ, the JSON output, is a feature incorporated to allow data extraction, markup cleaning etc. The arguments `exclude_markers` and `include_markers` in the methods `USFMParser.toUSJ()` makes this possible. Also the  `USFMParser.toList()`, can accept these inputs and perform similar operations. There is CLI versions also for these arguments to replicate the filtering feature there.
+
+- *excludeMarkers*
+
+  The first  input parameter to `toUSJ()` and `toList` of `USFMParser` class. Defaults to `null`. When proivded, all markers except those listed will be included in the output.
+
+- *includeMarkers*
+
+  The second input parameter to `toUSJ()` and `toList` of `USFMParser` class. Defaults to `null`. When proivded, only those markers listed will be included in the output. `includeMarkers` is applied before applying `excludeMarkers`. 
 
 
-### `USFMParser.toUSJ(): Object`
-Converts a USFM string to a USJ object.
+- *combineTexts*
 
-- `usfmString`: The input USFM string.
+   Fourth input parameter to `toUSJ()` and `toList` of `USFMParser` class. Defaults to `true`. After filtering out makers like paragraphs and characters, we are left with texts from within them, if 'text-in-excluded-parent' is also not excluded. These text snippets may come as separate components in the contents list. When this option is `True`, the consequetive text snippets will be concatinated together. The text concatination is done in a puctuation and space aware manner. If users need more control over the space handling or for any other reason, would prefer the texts snippets as different components in the output, this can be set to `False`.
 
-Returns: A JSON-like object representing the USJ.
+- *usfm_grammar.Filter*
 
-### `USFMParser.usjToUsfm(usjObject: Object): string`
-Converts a USJ object to a USFM string.
+  This Class provides a set of enums that would be useful in providing in the `excludeMarkers` and `includeMarkers` inputs rather than users listing out individual markers. The class has following options
+  ```
+    BOOK_HEADERS : identification and introduction markers
+    TITLES : section headings and associated markers
+    COMMENTS : comment markers like \rem
+    PARAGRAPHS : paragraph markers like \p, poetry markers, list table markers
+    CHARACTERS : all character level markups like \em, \w, \wj etc and their nested versions with +
+    NOTES : foot note, cross-reference and their content markers
+    STUDY_BIBLE : \esb and \cat
+    BCV : \id, \c and \v
+    TEXT : 'text-in-excluded-parent'
+    ```
+    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)
+    ``` 
+- Inner contents of excluded markers
 
-- `usjObject`: The input USJ object.
+  For markers like `\p` `\q` etc, by excluding them, we only remove them from the heirachy and retain the inner contents like `\v`, text etc that would be coming inside it. But for certain other markers like `\f`, `\x`, `\esb`  etc, if they are excluded their inner contents are also excluded. Following is the set of all markers, who inner contents are discarded if they are mentioned in `excludeMarkers` or not included in `includeMarkers`.
+  ```
+  BOOK_HEADERS, TITLES, COMMENTS, NOTES, STUDY_BIBLE
+  ```
+  :warning: Generally, it is recommended to NOT use both `exclude_markers` and `includeMarkers` together as it could lead to unexpected behavours and data loss. For instance if `include_makers` has `\fk` and `excludeMarkers` has `\f`, the output will not contain `\fk` as all inner contents of `\f` will be discarded.
 
-Returns: The converted USFM string.
 
 ## Contributing
-Contributions are welcome! If you find any issues or have suggestions for improvements, feel free to open an issue or create a pull request on [GitHub](https://github.com/your-username/usfm-grammar).
+Contributions are welcome! If you find any issues or have suggestions for improvements, feel free to open an issue or create a pull request on [GitHub](https://github.com/Bridgeconn/usfm-grammar).
 
 ## License
 This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

node-usfm-parser/package.json

@@ -1,7 +1,7 @@
 {
   "name": "usfm-grammar",
-  "version": "3.0.0-alpha.9",
-  "description": "Parser using tree-sitter-usfm3, to convert usfm to usj format.",
+  "version": "3.0.0-beta.15",
+  "description": "Uses the tree-sitter-usfm3 parser to convert USFM files to other formats such as USJ, USX, and CSV, and converts them back to USFM",
   "main": "./dist/cjs/index.cjs",
   "module": "./dist/es/index.mjs",
   "scripts": {
@@ -10,7 +10,7 @@
   },
   "repository": {
     "type": "git",
-    "url": "https://github.com/Bridgeconn/usfm-grammar/js-usfm-parser"
+    "url": "https://github.com/Bridgeconn/usfm-grammar"
   },
   "keywords": [
     "USFM",
@@ -28,7 +28,7 @@
   "dependencies": {
     "ajv": "^8.17.1",
     "tree-sitter": "0.21.1",
-    "tree-sitter-usfm3": "3.0.0-beta.9",
+    "tree-sitter-usfm3": "3.0.0-beta.15",
     "xmldom": "^0.6.0",
     "xpath": "^0.0.34"
   },

node-usfm-parser/src/usfmParser.js

@@ -173,7 +173,7 @@ Only one of USFM, USJ or USX is supported in one object.`)
 		if (!ignoreErrors && this.errors.length > 0) {
 			let errorString = this.errors.join("\n\t");
 			throw new Error(
-				`Errors present:\n\t${errorString}\nUse ignoreErrors = true to generate output despite errors.`,
+				`Errors present:\n\t${errorString}\nUse ignoreErrors = true, as third parameter of toUSJ(), to generate output despite errors.`,
 			);
 		}