pdf_to_hocr: improve plugin handling

2023-10-24 00:52:31 -07:00
parent 0443e87345
commit 68bb38d0ad
6 changed files with 43 additions and 5 deletions
@@ -414,6 +414,7 @@ def pdf_to_hocr(
    continue_on_soft_render_error: bool | None = None,
    invalidate_digital_signatures: bool | None = None,
    plugin_manager=None,
+    plugins: Iterable[StrPath] | None = None,
    keep_temporary_files: bool | None = None,
    **kwargs,
 ):
@@ -434,17 +435,18 @@ def pdf_to_hocr(
        # of code that use global state.

        if not plugin_manager:
-            plugin_manager = get_plugin_manager()
+            plugin_manager = get_plugin_manager(plugins)
        plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member

        cmdline, deferred = _kwargs_to_cmdline(
-            defer_kwargs={'input_pdf', 'output_folder'}, **create_options_kwargs
+            defer_kwargs={'input_pdf', 'output_folder', 'plugins'},
+            **create_options_kwargs,
        )
        cmdline.append(str(input_pdf))
        cmdline.append(str(output_folder))
        parser.enable_api_mode()
        options = parser.parse_args(cmdline)
-        for keyword, val in deferred:
+        for keyword, val in deferred.items():
            setattr(options, keyword, val)
        delattr(options, 'output_file')
        setattr(options, 'output_folder', output_folder)
@@ -0,0 +1,30 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+ <head>
+  <title></title>
+  <meta http-equiv="Content-Type" content="text/html;charset=utf-8"/>
+  <meta name='ocr-system' content='tesseract 5.3.2' />
+  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
+ </head>
+ <body>
+  <div class='ocr_page' id='page_1' title='image "/tmp/pytest-of-jb/pytest-25/popen-gw2/test_hocr_api0/000002_ocr.png"; bbox 0 0 9000 9000; ppageno 0; scan_res 300 300'>
+   <div class='ocr_carea' id='block_1_1' title="bbox 791 740 4415 1463">
+    <p class='ocr_par' id='par_1_1' lang='eng' title="bbox 791 740 4415 1463">
+     <span class='ocr_line' id='line_1_1' title="bbox 793 740 4415 1009; baseline -0.001 -51; x_size 274.5; x_descenders 57.5; x_ascenders 55.5">
+      <span class='ocrx_word' id='word_1_1' title='bbox 793 744 2238 958; x_wconf 34'>9OO0Ox9000</span>
+      <span class='ocrx_word' id='word_1_2' title='bbox 2350 740 3016 1009; x_wconf 92'>pixels</span>
+      <span class='ocrx_word' id='word_1_3' title='bbox 3120 752 3334 958; x_wconf 95'>at</span>
+      <span class='ocrx_word' id='word_1_4' title='bbox 3432 744 3914 958; x_wconf 75'>GOO</span>
+      <span class='ocrx_word' id='word_1_5' title='bbox 4025 740 4415 954; x_wconf 64'>DPI</span>
+     </span>
+     <span class='ocr_line' id='line_1_2' title="bbox 791 1190 2588 1463; baseline 0 -55; x_size 273; x_descenders 57; x_ascenders 55">
+      <span class='ocrx_word' id='word_1_6' title='bbox 791 1194 1045 1408; x_wconf 57'>S|]</span>
+      <span class='ocrx_word' id='word_1_7' title='bbox 1213 1190 2588 1463; x_wconf 59'>megapixels</span>
+     </span>
+    </p>
+   </div>
+  </div>
+ </body>
+</html>
@@ -0,0 +1,2 @@
+9OO0Ox9000 pixels at GOO DPI
+S|] megapixels
@@ -27,9 +27,13 @@ def test_stream_api(resources: Path):
    assert b'%PDF' in out.read(1024)


-def test_hocr_api(outdir):
+def test_hocr_api(resources: Path, outdir: Path):
    ocrmypdf.pdf_to_hocr(
-        'tests/resources/multipage.pdf', outdir, language='eng', skip_text=True
+        resources / 'multipage.pdf',
+        outdir,
+        language='eng',
+        skip_text=True,
+        plugins=['tests/plugins/tesseract_cache.py'],
    )
    assert (outdir / '000001_ocr_hocr.hocr').exists()
    assert (outdir / '000006_ocr_hocr.hocr').exists()