Allow disabling the html report.

README.md

@@ -46,12 +46,15 @@ Usage: dinglehopper [OPTIONS] GT OCR [REPORT_PREFIX]
   The metrics can be chosen via a comma separated combination of their acronyms
   like "--metrics=ca,wer,boc,bow".
 
+  The html report can be enabled/disabled using --html/--no-html.
+
   By default, the text of PAGE files is extracted on 'region' level. You may
   use "--textequiv-level line" to extract from the level of TextLine tags.
 
 Options:
   --metrics                 Enable different metrics like ca|cer, wa|wer, boc and bow.
   --textequiv-level LEVEL   PAGE TextEquiv level to extract text from
+  --html / --no-html        Enabling/disabling html report.
   --progress                Show progress bar
   --help                    Show this message and exit.
 ~~~
@@ -85,10 +88,11 @@ The OCR-D processor has these parameters:
 | ------------------------- | ------------------------------------------------------------------- |
 | `-P metrics cer,wer`      | Enable character error rate and word error rate (default)           |
 | `-P textequiv_level line` | (PAGE) Extract text from TextLine level (default: TextRegion level) |
+| `-P html false`           | Enabling/disabling html report (default: enabled).                  |
 
 For example:
 ~~~
-ocrd-dinglehopper -I ABBYY-FULLTEXT,OCR-D-OCR-CALAMARI -O OCR-D-OCR-COMPARE-ABBYY-CALAMARI -P metrics cer,wer
+ocrd-dinglehopper -I ABBYY-FULLTEXT,OCR-D-OCR-CALAMARI -O OCR-D-OCR-COMPARE-ABBYY-CALAMARI -P metrics cer,wer -P html false
 ~~~
 
 Developer information

qurator/dinglehopper/cli.py

@@ -144,7 +144,9 @@ def generate_json_report(gt, ocr, report_prefix, metrics_results):
         json.dump(json_dict, fp)
 
 
-def process(gt, ocr, report_prefix, *, metrics="cer,wer", textequiv_level="region"):
+def process(
+    gt, ocr, report_prefix, *, html=True, metrics="cer,wer", textequiv_level="region"
+):
     """Check OCR result against GT.
 
     The @click decorators change the signature of the decorated functions,
@@ -172,6 +174,7 @@ def process(gt, ocr, report_prefix, *, metrics="cer,wer", textequiv_level="regio
             metrics_results[result.metric] = result
 
     generate_json_report(gt, ocr, report_prefix, metrics_results)
+    if html:
         generate_html_report(gt, ocr, gt_text, ocr_text, report_prefix, metrics_results)
 
 
@@ -179,6 +182,7 @@ def process(gt, ocr, report_prefix, *, metrics="cer,wer", textequiv_level="regio
 @click.argument("gt", type=click.Path(exists=True))
 @click.argument("ocr", type=click.Path(exists=True))
 @click.argument("report_prefix", type=click.Path(), default="report")
+@click.option("--html", default=True, is_flag=True, help="Enable/disable html report.")
 @click.option(
     "--metrics",
     default="cer,wer",
@@ -191,7 +195,7 @@ def process(gt, ocr, report_prefix, *, metrics="cer,wer", textequiv_level="regio
     metavar="LEVEL",
 )
 @click.option("--progress", default=False, is_flag=True, help="Show progress bar")
-def main(gt, ocr, report_prefix, metrics, textequiv_level, progress):
+def main(gt, ocr, report_prefix, html, metrics, textequiv_level, progress):
     """
     Compare the PAGE/ALTO/text document GT against the document OCR.
 
@@ -210,12 +214,21 @@ def main(gt, ocr, report_prefix, metrics, textequiv_level, progress):
     The metrics can be chosen via a comma separated combination of their acronyms
     like "--metrics=ca,wer,boc,bow".
 
+    The html report can be enabled/disabled using --html / --no-html.
+
     By default, the text of PAGE files is extracted on 'region' level. You may
     use "--textequiv-level line" to extract from the level of TextLine tags.
     """
     initLogging()
     Config.progress = progress
-    process(gt, ocr, report_prefix, metrics=metrics, textequiv_level=textequiv_level)
+    process(
+        gt,
+        ocr,
+        report_prefix,
+        html=html,
+        metrics=metrics,
+        textequiv_level=textequiv_level,
+    )
 
 
 if __name__ == "__main__":

qurator/dinglehopper/ocrd-tool.json

@@ -18,6 +18,11 @@
         "recognition/text-recognition"
       ],
       "parameters": {
+        "html": {
+          "type": "boolean",
+          "default": true,
+          "description": "Enable/disable html report."
+        },
         "metrics": {
           "type": "string",
           "enum": ["", "boc", "boc,bow", "bow", "ca", "ca,boc", "ca,boc,bow", "ca,bow", "ca,wa", "ca,wa,boc", "ca,wa,boc,bow", "ca,wa,bow", "ca,wer", "ca,wer,boc", "ca,wer,boc,bow", "ca,wer,bow", "cer", "cer,boc", "cer,boc,bow", "cer,bow", "cer,wa", "cer,wa,boc", "cer,wa,boc,bow", "cer,wa,bow", "cer,wer", "cer,wer,boc", "cer,wer,boc,bow", "cer,wer,bow", "wa", "wa,boc", "wa,boc,bow", "wa,bow", "wer", "wer,boc", "wer,boc,bow", "wer,bow"],
@@ -28,7 +33,7 @@
           "type": "string",
           "enum": ["region", "line"],
           "default": "region",
-          "description": "PAGE XML hierarchy level to extract the text from"
+          "description": "PAGE XML hierarchy level to extract the text from."
         }
       }
     }

qurator/dinglehopper/ocrd_cli.py

@@ -30,6 +30,7 @@ class OcrdDinglehopperEvaluate(Processor):
 
         log = getLogger("processor.OcrdDinglehopperEvaluate")
 
+        html = self.parameter["html"]
         metrics = self.parameter["metrics"]
         textequiv_level = self.parameter["textequiv_level"]
         gt_grp, ocr_grp = self.input_file_grp.split(",")
@@ -57,15 +58,16 @@ class OcrdDinglehopperEvaluate(Processor):
                 gt_file.local_filename,
                 ocr_file.local_filename,
                 report_prefix,
+                html=html,
                 metrics=metrics,
                 textequiv_level=textequiv_level,
             )
 
             # Add reports to the workspace
-            for report_suffix, mimetype in [
+            report_types = [(".json", "application/json")]
-                [".html", "text/html"],
+            if html:
-                [".json", "application/json"],
+                report_types.append((".html", "text/html"))
-            ]:
+            for report_suffix, mimetype in report_types:
                 self.workspace.add_file(
                     ID=file_id + report_suffix,
                     file_grp=self.output_file_grp,

qurator/dinglehopper/tests/test_integ_cli.py

@@ -1,3 +1,5 @@
+from pathlib import Path
+
 import pytest
 
 from .util import working_directory
@@ -16,3 +18,19 @@ def test_cli_unknown_metric(tmp_path):
 
         with pytest.raises(ValueError, match="Unknown metric 'unknown'."):
             process("gt.txt", "ocr.txt", "report", metrics="cer,unknown")
+
+
+@pytest.mark.integration
+def test_cli_html_report_parameter(tmp_path):
+    """Test that html report can get turned off."""
+
+    with working_directory(str(tmp_path)):
+        with open("gt.txt", "w") as gtf:
+            gtf.write("")
+        with open("ocr.txt", "w") as ocrf:
+            ocrf.write("")
+
+        process("gt.txt", "ocr.txt", "report", html=False)
+
+        assert Path("report").with_suffix(".json").exists()
+        assert not Path("report").with_suffix(".html").exists()

qurator/dinglehopper/tests/test_integ_cli_valid_json.py

@@ -1,5 +1,6 @@
 import json
 from itertools import combinations
+from pathlib import Path
 
 import pytest
 
@@ -45,11 +46,10 @@ def test_cli_json(metrics, tmp_path):
         with open("ocr.txt", "w") as ocrf:
             ocrf.write("AAAAB")
 
-        with open("gt.txt", "r") as gtf:
-            print(gtf.read())
         process("gt.txt", "ocr.txt", "report", metrics=",".join(metrics))
-        with open("report.json", "r") as jsonf:
+
-            print(jsonf.read())
+        for suffix in (".json", ".html"):
+            assert Path("report").with_suffix(suffix).exists()
 
         with open("report.json", "r") as jsonf:
             j = json.load(jsonf)
@@ -76,6 +76,10 @@ def test_cli_json_extremes(gt, ocr, err, tmp_path):
             ocrf.write(ocr)
 
         process("gt.txt", "ocr.txt", "report", metrics="ca,wa,boc,bow")
+
+        for suffix in (".json", ".html"):
+            assert Path("report").with_suffix(suffix).exists()
+
         with open("report.json", "r") as jsonf:
             j = json.load(jsonf)
             for metric in set(METRIC_DICT.values()):