🎉 Initial commit

.gitignore

@@ -0,0 +1,108 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+# vim tmp
+*.swp
+*.swo

ocrd_repair_inconsistencies/cli.py

@@ -0,0 +1,10 @@
+import click
+
+from ocrd.decorators import ocrd_cli_options, ocrd_cli_wrap_processor
+from ocrd_repair_inconsistencies.ocrd_repair_inconsistencies import RepairInconsistencies
+
+
+@click.command()
+@ocrd_cli_options
+def ocrd_repair_inconsistencies(*args, **kwargs):
+    return ocrd_cli_wrap_processor(RepairInconsistencies, *args, **kwargs)

ocrd_repair_inconsistencies/config.py

@@ -0,0 +1,4 @@
+import json
+from pkg_resources import resource_string
+
+OCRD_TOOL = json.loads(resource_string(__name__, 'ocrd-tool.json').decode('utf8'))

ocrd_repair_inconsistencies/ocrd-tool.json

@@ -0,0 +1,22 @@
+{
+  "tools": {
+    "ocrd_repair_inconsistencies": {
+      "executable": "ocrd_repair_inconsistencies",
+      "categories": [
+        "Layout analysis"
+      ],
+      "description": "Repair glyph/word/line order inconsistencies",
+      "input_file_grp": [
+        "OCR-D-SEG-BLOCK"
+      ],
+      "output_file_grp": [
+        "OCR-D-SEG-BLOCK-FIXED"
+      ],
+      "steps": [
+        "layout/segmentation/region",
+        "layout/segmentation/line",
+        "layout/segmentation/words"
+      ]
+    }
+  }
+}

ocrd_repair_inconsistencies/ocrd_repair_inconsistencies.py

@@ -0,0 +1,114 @@
+from __future__ import absolute_import
+
+import os.path
+from collections import Sequence
+
+from shapely.geometry import Polygon, LineString
+
+from ocrd import Processor
+from ocrd_utils import (
+    getLogger, concat_padded,
+    coordinates_for_segment,
+    coordinates_of_segment,
+    polygon_from_points,
+    points_from_polygon,
+    xywh_from_polygon,
+    MIMETYPE_PAGE
+)
+from ocrd_modelfactory import page_from_file
+from ocrd_models.ocrd_page import (
+    CoordsType,
+    LabelType, LabelsType,
+    MetadataItemType,
+    to_xml
+)
+from ocrd_models.ocrd_page_generateds import (
+    RegionRefType,
+    RegionRefIndexedType,
+    OrderedGroupType,
+    OrderedGroupIndexedType,
+    UnorderedGroupType,
+    UnorderedGroupIndexedType,
+    ReadingOrderType
+)
+from .config import OCRD_TOOL
+
+TOOL = 'ocrd_repair_inconsistencies'
+LOG = getLogger('processor.RepairInconsistencies')
+
+class RepairInconsistencies(Processor):
+
+    def __init__(self, *args, **kwargs):
+        kwargs['ocrd_tool'] = OCRD_TOOL['tools'][TOOL]
+        super(RepairInconsistencies, self).__init__(*args, **kwargs)
+
+    def process(self):
+        for (n, input_file) in enumerate(self.input_files):
+            page_id = input_file.pageId or input_file.ID
+            LOG.info("INPUT FILE %i / %s", n, page_id)
+            pcgts = page_from_file(self.workspace.download_file(input_file))
+            page = pcgts.get_Page()
+
+            regions = page.get_TextRegion()
+            for region in regions:
+
+                lines = region.get_TextLine()
+                for line in lines:
+
+                    # Fix words in lines
+                    words = line.get_Word()
+                    line_text = get_text(line)
+                    words_text = get_text(words, ' ')
+                    if line_text != words_text:
+                        # XXX Assumes left-to-right
+                        sorted_words = sorted(words, key=lambda w: Polygon(polygon_from_points(w.get_Coords().points)).centroid.x)
+                        sorted_words_text = get_text(sorted_words, ' ')
+
+                        if sorted_words_text == line_text:
+                            LOG.info('Fixing word order of line "%s"', line.id)
+                            line.set_Word(sorted_words)
+
+                    words = line.get_Word()
+                    for word in words:
+
+                        # Fix glyphs in words
+                        glyphs = word.get_Glyph()
+                        word_text = get_text(word)
+                        glyphs_text = get_text(glyphs, '')
+                        if word_text != glyphs_text:
+                            # XXX Assumes left-to-right
+                            sorted_glyphs = sorted(glyphs, key=lambda g: Polygon( polygon_from_points(g.get_Coords().points)).centroid.x)
+                            sorted_glyphs_text = get_text(sorted_glyphs, '')
+
+                            if sorted_glyphs_text == word_text:
+                                LOG.info('Fixing glyph order of word "%s"', word.id)
+                                word.set_Glyph(sorted_glyphs)
+
+            file_id = input_file.ID.replace(self.input_file_grp, self.output_file_grp)
+            if file_id == input_file.ID:
+                file_id = concat_padded(self.output_file_grp, n)
+            self.workspace.add_file(
+                ID=file_id,
+                file_grp=self.output_file_grp,
+                pageId=input_file.pageId,
+                mimetype=MIMETYPE_PAGE,
+                local_filename=os.path.join(self.output_file_grp, file_id + '.xml'),
+                content=to_xml(pcgts))
+
+
+
+def get_text(thing, joiner=None):
+    """Get the text of the given thing, joining if necessary"""
+
+    def _get_text_for_one(t):
+        # XXX Assumes len(TextEquiv) == 1
+        try:
+            return t.get_TextEquiv()[0].get_Unicode()
+        except Exception:
+            return None
+
+    if isinstance(thing, Sequence):
+        text = joiner.join(_get_text_for_one(t) for t in thing)
+    else:
+        text = _get_text_for_one(thing)
+    return text

requirements.txt

@@ -0,0 +1,3 @@
+click
+shapely
+ocrd

setup.py

@@ -0,0 +1,23 @@
+# -*- coding: utf-8 -*-
+import codecs
+
+from setuptools import setup, find_packages
+
+setup(
+    name='ocrd_repair_inconsistencies',
+    description='Repair glyph/word/line order inconsistencies',
+    #long_description=codecs.open('README.md', encoding='utf-8').read(),
+    author='Mike Gerber',
+    author_email='mike.gerber@sbb.spk-berlin.de',
+    license='Apache License 2.0',
+    packages=find_packages(exclude=('tests', 'docs')),
+    install_requires=open('requirements.txt').read().split('\n'),
+    package_data={
+        '': ['*.json', '*.yml', '*.yaml'],
+    },
+    entry_points={
+        'console_scripts': [
+            'ocrd_repair_inconsistencies=ocrd_repair_inconsistencies.cli:ocrd_repair_inconsistencies',
+        ]
+    },
+)