v11.4.2 release notes

Closes #701

docs/release_notes.rst

@@ -12,6 +12,12 @@ may be unreliable. Use the API to depend on precise behavior.
 The public API may be useful in scripts that launch OCRmyPDF processes or that
 wish to use some of its features for working with PDFs.
 
+v11.4.2
+=======
+
+-  Fixed support for Cygwin, hopefully.
+-  watcher.py: Fixed an issue with the OCR_LOGLEVEL not being interpreted.
+
 v11.4.1
 =======
 

misc/watcher.py

@@ -44,7 +44,7 @@ DESKEW = bool(os.getenv('OCR_DESKEW', ''))
 OCR_JSON_SETTINGS = json.loads(os.getenv('OCR_JSON_SETTINGS', '{}'))
 POLL_NEW_FILE_SECONDS = int(os.getenv('OCR_POLL_NEW_FILE_SECONDS', '1'))
 USE_POLLING = bool(os.getenv('OCR_USE_POLLING', ''))
-LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO').upper()
+LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO')
 PATTERNS = ['*.pdf', '*.PDF']
 
 log = logging.getLogger('ocrmypdf-watcher')
@@ -117,7 +117,12 @@ class HandleObserverEvent(PatternMatchingEventHandler):
 
 def main():
     ocrmypdf.configure_logging(
-        verbosity=ocrmypdf.Verbosity.default, manage_root_logger=True
+        verbosity=(
+            ocrmypdf.Verbosity.default
+            if LOGLEVEL != 'DEBUG'
+            else ocrmypdf.Verbosity.debug
+        ),
+        manage_root_logger=True,
     )
     log.setLevel(LOGLEVEL)
     log.info(
@@ -135,7 +140,7 @@ def main():
         f"ARGS: {OCR_JSON_SETTINGS}\n"
         f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"
         f"USE_POLLING: {USE_POLLING}\n"
-        f"LOGLEVEL: {LOGLEVEL}\n"
+        f"LOGLEVEL: {LOGLEVEL}"
     )
 
     if 'input_file' in OCR_JSON_SETTINGS or 'output_file' in OCR_JSON_SETTINGS:

src/ocrmypdf/_concurrent.py

@@ -12,6 +12,7 @@ import os
 import signal
 import sys
 import threading
+from contextlib import suppress
 from multiprocessing import Pool as ProcessPool
 from multiprocessing.dummy import Pool as ThreadPool
 from typing import Callable, Iterable, Optional
@@ -56,7 +57,7 @@ def process_init(queue, user_init, loglevel):
     signal.signal(signal.SIGINT, signal.SIG_IGN)
 
     # Install SIGBUS handler (so our parent process can abort somewhat gracefully)
-    if hasattr(signal, 'SIGBUS'):
+    with suppress(AttributeError):  # Windows and Cygwin do not have SIGBUS
         signal.signal(signal.SIGBUS, process_sigbus)
 
     # Reconfigure the root logger for this process to send all messages to a queue
@@ -72,7 +73,8 @@ def process_init(queue, user_init, loglevel):
 
 def thread_init(_queue, user_init, _loglevel):
     # As a thread, block SIGBUS so the main thread deals with it...
-    if hasattr(signal, 'SIGBUS'):
+    with suppress(AttributeError):
+        # Windows and Cygwin do not have pthread_sigmask or SIGBUS
         signal.pthread_sigmask(signal.SIG_BLOCK, {signal.SIGBUS})
     if user_init:
         user_init()

src/ocrmypdf/_pipeline.py

@@ -150,7 +150,7 @@ def get_pdfinfo(
     progbar=False,
     max_workers=None,
     check_pages=None,
-):
+) -> PdfInfo:
     try:
         return PdfInfo(
             input_file,

src/ocrmypdf/pdfinfo/info.py

@@ -15,11 +15,11 @@ from functools import partial
 from math import hypot, isclose
 from os import PathLike
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Container, Dict, Iterator, List, Optional, Tuple, Union
 from warnings import warn
 
 import pikepdf
-from pikepdf import PdfMatrix
+from pikepdf import Object, Pdf, PdfMatrix
 
 from ocrmypdf._concurrent import exec_progress_pool
 from ocrmypdf.exceptions import EncryptedPdfError
@@ -115,7 +115,7 @@ def _normalize_stack(graphobjs):
             yield (operands, operator)
 
 
-def _interpret_contents(contentstream, initial_shorthand=UNIT_SQUARE):
+def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
     """Interpret the PDF content stream.
 
     The stack represents the state of the PDF graphics stack.  We are only
@@ -204,7 +204,7 @@ def _interpret_contents(contentstream, initial_shorthand=UNIT_SQUARE):
     )
 
 
-def _get_dpi(ctm_shorthand, image_size):
+def _get_dpi(ctm_shorthand, image_size) -> Resolution:
     """Given the transformation matrix and image size, find the image DPI.
 
     PDFs do not include image resolution information within image data.
@@ -271,8 +271,14 @@ def _get_dpi(ctm_shorthand, image_size):
 class ImageInfo:
     DPI_PREC = Decimal('1.000')
 
-    def __init__(self, *, name='', pdfimage=None, inline=None, shorthand=None):
-
+    def __init__(
+        self,
+        *,
+        name='',
+        pdfimage: Optional[Object] = None,
+        inline: Optional[Object] = None,
+        shorthand=None,
+    ):
         self._name = str(name)
         self._shorthand = shorthand
 
@@ -282,6 +288,8 @@ class ImageInfo:
         elif pdfimage is not None:
             self._origin = 'xobject'
             pim = pikepdf.PdfImage(pdfimage)
+        else:
+            raise ValueError("Either pdfimage or inline must be set")
         self._width = pim.width
         self._height = pim.height
 
@@ -371,7 +379,7 @@ class ImageInfo:
         ).format(**class_locals)
 
 
-def _find_inline_images(contentsinfo):
+def _find_inline_images(contentsinfo: ContentsInfo) -> Iterator[ImageInfo]:
     "Find inline images in the contentstream"
 
     for n, inline in enumerate(contentsinfo.inline_images):
@@ -380,7 +388,7 @@ def _find_inline_images(contentsinfo):
         )
 
 
-def _image_xobjects(container):
+def _image_xobjects(container) -> Iterator[Tuple[Object, str]]:
     """Search for all XObject-based images in the container
 
     Usually the container is a page, but it could also be a Form XObject
@@ -400,7 +408,7 @@ def _image_xobjects(container):
         return
     xobjs = resources['/XObject'].as_dict()
     for xobj in xobjs:
-        candidate = xobjs[xobj]
+        candidate: Object = xobjs[xobj]
         if not '/Subtype' in candidate:
             continue
         if candidate['/Subtype'] == '/Image':
@@ -408,7 +416,9 @@ def _image_xobjects(container):
             yield (pdfimage, xobj)
 
 
-def _find_regular_images(container, contentsinfo):
+def _find_regular_images(
+    container: Object, contentsinfo: ContentsInfo
+) -> Iterator[ImageInfo]:
     """Find images stored in the container's /Resources /XObject
 
     Usually the container is a page, but it could also be a Form XObject
@@ -432,7 +442,7 @@ def _find_regular_images(container, contentsinfo):
             yield ImageInfo(name=draw.name, pdfimage=pdfimage, shorthand=draw.shorthand)
 
 
-def _find_form_xobject_images(pdf, container, contentsinfo):
+def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: ContentsInfo):
     """Find any images that are in Form XObjects in the container
 
     The container may be a page, or a parent Form XObject.
@@ -464,7 +474,9 @@ def _find_form_xobject_images(pdf, container, contentsinfo):
             )
 
 
-def _process_content_streams(*, pdf, container, shorthand=None):
+def _process_content_streams(
+    *, pdf: Pdf, container: Object, shorthand=None
+) -> Iterator[Union[VectorMarker, TextMarker, ImageInfo]]:
     """Find all individual instances of images drawn in the container
 
     Usually the container is a page, but it may also be a Form XObject.
@@ -526,7 +538,7 @@ def _page_has_text(text_blocks, page_width, page_height) -> bool:
         margin_ratio * ph,  # bottom  (first quadrant: bottom < top)
     )
 
-    def rects_intersect(a, b):
+    def rects_intersect(a, b) -> bool:
         """
         Where (a,b) are 4-tuple rects (left-0, top-1, right-2, bottom-3)
         https://stackoverflow.com/questions/306316/determine-if-two-rectangles-overlap-each-other
@@ -542,7 +554,7 @@ def _page_has_text(text_blocks, page_width, page_height) -> bool:
     return has_text
 
 
-def simplify_textboxes(miner, textbox_getter):
+def simplify_textboxes(miner, textbox_getter) -> Iterator[TextboxInfo]:
     """Extract only limited content from text boxes
 
     We do this to save memory and ensure that our objects are pickleable.
@@ -556,74 +568,6 @@ def simplify_textboxes(miner, textbox_getter):
         yield TextboxInfo(box.bbox, visible, corrupt)
 
 
-def _pdf_get_pageinfo(
-    pdf, pageno: int, infile: PathLike, check_pages, detailed_analysis: bool
-):
-    pageinfo: Dict[str, Any] = {}
-    pageinfo['pageno'] = pageno
-    pageinfo['images'] = []
-
-    page = pdf.pages[pageno]
-    mediabox = [Decimal(d) for d in page.MediaBox.as_list()]
-    width_pt = mediabox[2] - mediabox[0]
-    height_pt = mediabox[3] - mediabox[1]
-
-    check_this_page = pageno in check_pages
-
-    if check_this_page and detailed_analysis:
-        pscript5_mode = str(pdf.docinfo.get('/Creator')).startswith('PScript5')
-        miner = get_page_analysis(infile, pageno, pscript5_mode)
-        pageinfo['textboxes'] = list(simplify_textboxes(miner, get_text_boxes))
-        bboxes = (box.bbox for box in pageinfo['textboxes'])
-
-        pageinfo['has_text'] = _page_has_text(bboxes, width_pt, height_pt)
-    else:
-        pageinfo['textboxes'] = []
-        pageinfo['has_text'] = None  # i.e. "no information"
-
-    userunit = page.get('/UserUnit', Decimal(1.0))
-    if not isinstance(userunit, Decimal):
-        userunit = Decimal(userunit)
-    pageinfo['userunit'] = userunit
-    pageinfo['width_inches'] = width_pt * userunit / Decimal(72.0)
-    pageinfo['height_inches'] = height_pt * userunit / Decimal(72.0)
-
-    try:
-        pageinfo['rotate'] = int(page['/Rotate'])
-    except KeyError:
-        pageinfo['rotate'] = 0
-
-    userunit_shorthand = (userunit, 0, 0, userunit, 0, 0)
-
-    if check_this_page:
-        pageinfo['has_vector'] = False
-        pageinfo['has_text'] = False
-        pageinfo['images'] = []
-        for ci in _process_content_streams(
-            pdf=pdf, container=page, shorthand=userunit_shorthand
-        ):
-            if isinstance(ci, VectorMarker):
-                pageinfo['has_vector'] = True
-            elif isinstance(ci, TextMarker):
-                pageinfo['has_text'] = True
-            elif isinstance(ci, ImageInfo):
-                pageinfo['images'].append(ci)
-            else:
-                raise NotImplementedError()
-    else:
-        pageinfo['has_vector'] = None  # i.e. "no information"
-        pageinfo['has_text'] = None
-        pageinfo['images'] = None
-
-    if pageinfo['images']:
-        dpi = Resolution(0.0, 0.0).take_max(image.dpi for image in pageinfo['images'])
-        pageinfo['dpi'] = dpi
-        pageinfo['width_pixels'] = int(round(dpi.x * float(pageinfo['width_inches'])))
-        pageinfo['height_pixels'] = int(round(dpi.y * float(pageinfo['height_inches'])))
-
-    return pageinfo
-
-
 worker_pdf = None
 
 
@@ -693,13 +637,85 @@ def _pdf_pageinfo_concurrent(
 
 
 class PageInfo:
-    def __init__(self, pdf, pageno, infile, check_pages, detailed_analysis=False):
+    def __init__(
+        self,
+        pdf: Pdf,
+        pageno: int,
+        infile: PathLike,
+        check_pages: Container[int],
+        detailed_analysis: bool = False,
+    ):
         self._pageno = pageno
         self._infile = infile
         self._detailed_analysis = detailed_analysis
-        self._pageinfo = _pdf_get_pageinfo(
-            pdf, pageno, infile, check_pages, detailed_analysis
-        )
+        self._gather_pageinfo(pdf, pageno, infile, check_pages, detailed_analysis)
+
+    def _gather_pageinfo(
+        self,
+        pdf: Pdf,
+        pageno: int,
+        infile: PathLike,
+        check_pages: Container[int],
+        detailed_analysis: bool,
+    ):
+        page = pdf.pages[pageno]
+        mediabox = [Decimal(d) for d in page.MediaBox.as_list()]
+        width_pt = mediabox[2] - mediabox[0]
+        height_pt = mediabox[3] - mediabox[1]
+
+        check_this_page = pageno in check_pages
+
+        if check_this_page and detailed_analysis:
+            pscript5_mode = str(pdf.docinfo.get('/Creator')).startswith('PScript5')
+            miner = get_page_analysis(infile, pageno, pscript5_mode)
+            self._textboxes = list(simplify_textboxes(miner, get_text_boxes))
+            bboxes = (box.bbox for box in self._textboxes)
+
+            self._has_text = _page_has_text(bboxes, width_pt, height_pt)
+        else:
+            self._textboxes = []
+            self._has_text = None  # i.e. "no information"
+
+        userunit = page.get('/UserUnit', Decimal(1.0))
+        if not isinstance(userunit, Decimal):
+            userunit = Decimal(userunit)
+        self._userunit = userunit
+        self._width_inches = width_pt * userunit / Decimal(72.0)
+        self._height_inches = height_pt * userunit / Decimal(72.0)
+
+        try:
+            self._rotate = int(page['/Rotate'])
+        except KeyError:
+            self._rotate = 0
+
+        userunit_shorthand = (userunit, 0, 0, userunit, 0, 0)
+
+        if check_this_page:
+            self._has_vector = False
+            self._has_text = False
+            self._images = []
+            for ci in _process_content_streams(
+                pdf=pdf, container=page, shorthand=userunit_shorthand
+            ):
+                if isinstance(ci, VectorMarker):
+                    self._has_vector = True
+                elif isinstance(ci, TextMarker):
+                    self._has_text = True
+                elif isinstance(ci, ImageInfo):
+                    self._images.append(ci)
+                else:
+                    raise NotImplementedError()
+        else:
+            self._has_vector = None  # i.e. "no information"
+            self._has_text = None
+            self._images = None
+
+        self._dpi = None
+        if self._images:
+            dpi = Resolution(0.0, 0.0).take_max(image.dpi for image in self._images)
+            self._dpi = dpi
+            self._width_pixels = int(round(dpi.x * float(self._width_inches)))
+            self._height_pixels = int(round(dpi.y * float(self._height_inches)))
 
     @property
     def pageno(self) -> int:
@@ -707,25 +723,25 @@ class PageInfo:
 
     @property
     def has_text(self) -> bool:
-        return self._pageinfo['has_text']
+        return self._has_text
 
     @property
     def has_corrupt_text(self) -> bool:
         if not self._detailed_analysis:
             raise NotImplementedError('Did not do detailed analysis')
-        return any(tbox.is_corrupt for tbox in self._pageinfo['textboxes'])
+        return any(tbox.is_corrupt for tbox in self._textboxes)
 
     @property
     def has_vector(self) -> bool:
-        return self._pageinfo['has_vector']
+        return self._has_vector
 
     @property
     def width_inches(self) -> Decimal:
-        return self._pageinfo['width_inches']
+        return self._width_inches
 
     @property
     def height_inches(self) -> Decimal:
-        return self._pageinfo['height_inches']
+        return self._height_inches
 
     @property
     def width_pixels(self) -> int:
@@ -737,18 +753,18 @@ class PageInfo:
 
     @property
     def rotation(self) -> int:
-        return self._pageinfo.get('rotate', None)
+        return self._rotate
 
     @rotation.setter
     def rotation(self, value):
         if value in (0, 90, 180, 270, 360, -90, -180, -270):
-            self._pageinfo['rotate'] = value
+            self._rotate = value
         else:
             raise ValueError("rotation must be a cardinal angle")
 
     @property
     def images(self):
-        return self._pageinfo['images']
+        return self._images
 
     def get_textareas(
         self, visible: Optional[bool] = None, corrupt: Optional[bool] = None
@@ -763,24 +779,22 @@ class PageInfo:
                     result = False
             return result
 
-        if 'textboxes' not in self._pageinfo:
+        if not self._textboxes:
             if visible is not None and corrupt is not None:
                 raise NotImplementedError('Incomplete information on textboxes')
-            return self._pageinfo['bboxes']
+            return self._textboxes
 
-        return (
-            obj.bbox
-            for obj in self._pageinfo['textboxes']
-            if predicate(obj, visible, corrupt)
-        )
+        return (obj.bbox for obj in self._textboxes if predicate(obj, visible, corrupt))
 
     @property
     def dpi(self) -> Resolution:
-        return self._pageinfo.get('dpi', Resolution(0.0, 0.0))
+        if self._dpi is None:
+            return Resolution(0.0, 0.0)
+        return self._dpi
 
     @property
     def userunit(self) -> Decimal:
-        return self._pageinfo.get('userunit', None)
+        return self._userunit
 
     @property
     def min_version(self) -> str:

src/ocrmypdf/pdfinfo/layout.py

@@ -223,6 +223,7 @@ def get_page_analysis(infile, pageno, pscript5_mode):
     )
     interp = pdfminer.pdfinterp.PDFPageInterpreter(rman, dev)
 
+    patcher = None
     if pscript5_mode:
         patcher = patch.multiple(
             'pdfminer.pdffont.PDFType3Font',
@@ -237,10 +238,10 @@ def get_page_analysis(infile, pageno, pscript5_mode):
         with Path(infile).open('rb') as f:
             page = PDFPage.get_pages(f, pagenos=[pageno], maxpages=0)
             interp.process_page(next(page))
-    except PDFTextExtractionNotAllowed:
-        raise EncryptedPdfError()
+    except PDFTextExtractionNotAllowed as e:
+        raise EncryptedPdfError() from e
     finally:
-        if pscript5_mode:
+        if patcher is not None:
             patcher.stop()
 
     return dev.get_result()

tests/test_main.py

@@ -92,10 +92,10 @@ def test_skip_ocr(resources, outpdf):
 
 def test_redo_ocr(resources, outpdf):
     in_ = resources / 'graph_ocred.pdf'
-    before = PdfInfo(in_)
+    before = PdfInfo(in_, detailed_analysis=True)
     out = outpdf
     out = check_ocrmypdf(in_, out, '--redo-ocr')
-    after = PdfInfo(out)
+    after = PdfInfo(out, detailed_analysis=True)
     assert before[0].has_text and after[0].has_text
     assert (
         before[0].get_textareas() != after[0].get_textareas()