Port to ocrd core version 3.0.0

.github/workflow/tests.yml

@@ -0,0 +1,33 @@
+name: Test ocrd_cis installation and run tests
+
+on:
+  push:
+  pull_request:
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: [ "3.8", "3.9", "3.10", "3.11", "3.12" ]
+        os: [ "ubuntu-22.04" ]
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.head_ref }}
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - uses: actions/setup-java@v4
+        with:
+          distribution: 'zulu'
+          java-version: '11'
+      - name: Install ocrd_cis
+        run: make install
+      - name: Test ocrd_cis
+        run: make test V=""

ocrd_cis/__init__.py

@@ -1,3 +1,2 @@
 from .javaprocess import JavaAligner
 from .javaprocess import JavaPostCorrector
-from .ocrd_tool import get_ocrd_tool

ocrd_cis/data/__main__.py

@@ -1,18 +1,18 @@
-import pkg_resources
 import sys
+from ocrd_utils import resource_filename
 
 def main():
     usage = 'usage: ' + sys.argv[0] + ' -jar|-3gs|-model|-config'
     if '-h' in sys.argv:
         print(usage)
     elif '-jar' in sys.argv:
-        print(pkg_resources.resource_filename('ocrd_cis', 'data/ocrd-cis.jar'))
+        print(resource_filename('ocrd_cis', 'data/ocrd-cis.jar'))
     elif '-3gs' in sys.argv:
-        print(pkg_resources.resource_filename('ocrd_cis', 'data/3gs.csv.gz'))
+        print(resource_filename('ocrd_cis', 'data/3gs.csv.gz'))
     elif '-model' in sys.argv:
-        print(pkg_resources.resource_filename('ocrd_cis', 'data/model.zip'))
+        print(resource_filename('ocrd_cis', 'data/model.zip'))
     elif '-config' in sys.argv:
-        print(pkg_resources.resource_filename('ocrd_cis', 'data/config.json'))
+        print(resource_filename('ocrd_cis', 'data/config.json'))
     else:
         raise ValueError(usage)
 

ocrd_cis/javaprocess.py

@@ -1,12 +1,11 @@
 import subprocess
 import json
-import pkg_resources
 
-from ocrd_utils import getLogger
+from ocrd_utils import getLogger, resource_filename
 from pathlib import Path
 
 MAIN = "de.lmu.cis.ocrd.cli.Main"
-JAR = pkg_resources.resource_filename('ocrd_cis', 'data/ocrd-cis.jar')
+JAR = str(resource_filename('ocrd_cis', 'data/ocrd-cis.jar'))
 
 def JavaAligner(n, loglvl):
     """Create a java process that calls -c align -D '{"n":n}'"""

ocrd_cis/ocrd-tool.json

@@ -12,17 +12,9 @@
 				"preprocessing/optimization/grayscale_normalization",
 				"preprocessing/optimization/deskewing"
 			],
-			"input_file_grp": [
-				"OCR-D-IMG",
-				"OCR-D-SEG-BLOCK",
-				"OCR-D-SEG-LINE"
-			],
-			"output_file_grp": [
-				"OCR-D-IMG-BIN",
-				"OCR-D-SEG-BLOCK",
-				"OCR-D-SEG-LINE"
-			],
-			"description": "Binarize (and optionally deskew/despeckle) pages / regions / lines with ocropy",
+			"input_file_grp_cardinality": 1,
+			"output_file_grp_cardinality": 1,
+			"description": "Binarize (and optionally deskew/despeckle) pages / regions / lines with Ocropy v1",
 			"parameters": {
 				"method": {
 					"type": "string",
@@ -75,15 +67,9 @@
 			"steps": [
 				"preprocessing/optimization/deskewing"
 			],
-			"input_file_grp": [
-				"OCR-D-SEG-BLOCK",
-				"OCR-D-SEG-LINE"
-			],
-			"output_file_grp": [
-				"OCR-D-SEG-BLOCK",
-				"OCR-D-SEG-LINE"
-			],
-			"description": "Deskew regions with ocropy (by annotating orientation angle and adding AlternativeImage)",
+			"input_file_grp_cardinality": 1,
+			"output_file_grp_cardinality": 1,
+			"description": "Deskew regions with Ocropy v1 (by annotating orientation angle and adding AlternativeImage)",
 			"parameters": {
 				"maxskew": {
 					"type": "number",
@@ -106,17 +92,9 @@
 			"steps": [
 				"preprocessing/optimization/despeckling"
 			],
-			"input_file_grp": [
-				"OCR-D-IMG",
-				"OCR-D-SEG-BLOCK",
-				"OCR-D-SEG-LINE"
-			],
-			"output_file_grp": [
-				"OCR-D-IMG-DESPECK",
-				"OCR-D-SEG-BLOCK",
-				"OCR-D-SEG-LINE"
-			],
-			"description": "Despeckle pages / regions / lines with ocropy",
+			"input_file_grp_cardinality": 1,
+			"output_file_grp_cardinality": 1,
+			"description": "Despeckle pages / regions / lines with Ocropy v1",
 			"parameters": {
 				"noise_maxsize": {
 					"type": "number",
@@ -147,14 +125,8 @@
 				"layout/segmentation/region",
 				"layout/segmentation/line"
 			],
-			"input_file_grp": [
-				"OCR-D-SEG-BLOCK",
-				"OCR-D-SEG-LINE"
-			],
-			"output_file_grp": [
-				"OCR-D-SEG-BLOCK",
-				"OCR-D-SEG-LINE"
-			],
+			"input_file_grp_cardinality": 1,
+			"output_file_grp_cardinality": 1,
 			"description": "Clip text regions / lines at intersections with neighbours",
 			"parameters": {
 				"level-of-operation": {
@@ -185,12 +157,8 @@
 			"steps": [
 				"layout/segmentation/line"
 			],
-			"input_file_grp": [
-				"OCR-D-SEG-LINE"
-			],
-			"output_file_grp": [
-				"OCR-D-SEG-LINE"
-			],
+			"input_file_grp_cardinality": 1,
+			"output_file_grp_cardinality": 1,
 			"description": "Improve coordinates of text lines",
 			"parameters": {
 				"level-of-operation": {
@@ -245,12 +213,8 @@
 				"preprocessing/optimization/dewarping"
 			],
 			"description": "Dewarp line images with ocropy",
-			"input_file_grp": [
-				"OCR-D-SEG-LINE"
-			],
-			"output_file_grp": [
-				"OCR-D-SEG-LINE"
-			],
+			"input_file_grp_cardinality": 1,
+			"output_file_grp_cardinality": 1,
 			"parameters": {
 				"dpi": {
 					"type": "number",
@@ -286,15 +250,9 @@
 			"steps": [
 				"recognition/text-recognition"
 			],
-			"description": "Recognize text in (binarized+deskewed+dewarped) lines with ocropy",
-			"input_file_grp": [
-				"OCR-D-SEG-LINE",
-				"OCR-D-SEG-WORD",
-				"OCR-D-SEG-GLYPH"
-			],
-			"output_file_grp": [
-				"OCR-D-OCR-OCRO"
-			],
+			"description": "Recognize text in (binarized+deskewed+dewarped) lines with Ocropy v1",
+			"input_file_grp_cardinality": 1,
+			"output_file_grp_cardinality": 1,
 			"parameters": {
 				"textequiv_level": {
 					"type": "string",
@@ -345,14 +303,9 @@
 				"layout/segmentation/region",
 				"layout/segmentation/line"
 			],
-			"input_file_grp": [
-				"OCR-D-GT-SEG-BLOCK",
-				"OCR-D-SEG-BLOCK"
-			],
-			"output_file_grp": [
-				"OCR-D-SEG-LINE"
-			],
-			"description": "Segment pages into regions and lines, tables into cells and lines, or regions into lines with ocropy",
+			"input_file_grp_cardinality": 1,
+			"output_file_grp_cardinality": 1,
+			"description": "Segment pages into regions and lines, tables into cells and lines, or regions into lines with Ocropy v1",
 			"parameters": {
 				"dpi": {
 					"type": "number",
@@ -444,11 +397,9 @@
 			"steps": [
 				"recognition/text-recognition"
 			],
-			"input_file_grp": [
-				"OCR-D-GT-SEG-BLOCK",
-				"OCR-D-SEG-BLOCK"
-			],
-			"description": "train model with ground truth from mets data",
+			"input_file_grp_cardinality": 1,
+			"output_file_grp_cardinality": 1,
+			"description": "train Ocropy v1 text recognition model with PAGE ground truth from the input fileGrp extracted as file pairs into the output fileGrp",
 			"parameters": {
 				"textequiv_level": {
 					"type": "string",
@@ -470,7 +421,8 @@
 				},
 				"outputpath": {
 					"type": "string",
-					"description": "(existing) path for the trained model"
+					"default": "output",
+					"description": "directory path for the trained model"
 				}
 			}
 		},
@@ -482,15 +434,9 @@
 			"steps": [
 				"recognition/post-correction"
 			],
-			"input_file_grp": [
-				"OCR-D-OCR-1",
-				"OCR-D-OCR-2",
-				"OCR-D-OCR-N"
-			],
-			"output_file_grp": [
-				"OCR-D-ALIGNED"
-			],
-			"description": "Align multiple OCRs and/or GTs"
+			"input_file_grp_cardinality": [2, -1],
+			"output_file_grp_cardinality": 1,
+			"description": "Align multiple OCRs and/or GTs textually on line/word level"
 		},
 		"ocrd-cis-postcorrect": {
 			"executable": "ocrd-cis-postcorrect",
@@ -501,12 +447,8 @@
 				"recognition/post-correction"
 			],
 			"description": "Post correct OCR results",
-			"input_file_grp": [
-				"OCR-D-LINE-ALIGNED"
-			],
-			"output_file_grp": [
-				"OCR-D-POST-CORRECTED"
-			],
+			"input_file_grp_cardinality": 1,
+			"output_file_grp_cardinality": 1,
 			"parameters": {
 				"maxCandidates": {
 					"description": "Maximum number of considered correction candidates per suspicious token",