Added line size metrics to output per #906 (#909)

package.json

@@ -69,7 +69,7 @@
     "node-fetch": "^2.6.9",
     "opencollective-postinstall": "^2.0.3",
     "regenerator-runtime": "^0.13.3",
-    "tesseract.js-core": "^5.0.0",
+    "tesseract.js-core": "^5.1.0",
     "wasm-feature-detect": "^1.2.11",
     "zlibjs": "^0.3.1"
   },

src/index.d.ts

@@ -178,6 +178,11 @@ declare namespace Tesseract {
     y1: number;
     has_baseline: boolean;
   }
+  interface RowAttributes {
+    ascenders: number;
+    descenders: number;
+    row_height: number;
+  }
   interface Bbox {
     x0: number;
     y0: number;
@@ -189,6 +194,7 @@ declare namespace Tesseract {
     text: string;
     confidence: number;
     baseline: Baseline;
+    rowAttributes: RowAttributes
     bbox: Bbox;
     paragraph: Paragraph;
     block: Block;

src/worker-script/utils/dump.js

@@ -126,11 +126,22 @@ module.exports = (TessModule, api, output, options) => {
         block.paragraphs.push(para);
       }
       if (ri.IsAtBeginningOf(RIL_TEXTLINE)) {
+        // getRowAttributes was added in a recent minor version of Tesseract.js-core,
+        // so we need to check if it exists before calling it.
+        // This can be removed in the next major version (v6).
+        let rowAttributes;
+        if (ri.getRowAttributes) {
+          rowAttributes = ri.getRowAttributes();
+          // Descenders is reported as a negative within Tesseract internally so we need to flip it.
+          // The positive version is intuitive, and matches what is reported in the hOCR output.
+          rowAttributes.descenders *= -1;
+        }
         textline = {
           words: [],
           text: !options.skipRecognition ? ri.GetUTF8Text(RIL_TEXTLINE) : null,
           confidence: !options.skipRecognition ? ri.Confidence(RIL_TEXTLINE) : null,
           baseline: ri.getBaseline(RIL_TEXTLINE),
+          rowAttributes,
           bbox: ri.getBoundingBox(RIL_TEXTLINE),
         };
         para.lines.push(textline);