Merge branch 'feature/misc-breaking'

src/ocrmypdf/_exec/ghostscript.py

@@ -166,6 +166,7 @@ class GhostscriptFollower:
 def generate_pdfa(
     pdf_pages,
     output_file: os.PathLike,
+    *,
     compression: str,
     pdf_version: str = '1.5',
     pdfa_part: str = '2',
@@ -195,10 +196,11 @@ def generate_pdfa(
             "-dAutoFilterGrayImages=true",
         ]
 
+    strategy = 'LeaveColorUnchanged'
     # Older versions of Ghostscript expect a leading slash in
     # sColorConversionStrategy, newer ones should not have it. See Ghostscript
     # git commit fe1c025d.
-    strategy = 'RGB' if version() >= '9.19' else '/RGB'
+    strategy = ('/' + strategy) if version() < '9.19' else strategy
 
     if version() == '9.23':
         # 9.23: added JPEG passthrough as a new feature, but with a bug that

src/ocrmypdf/_exec/tesseract.py

@@ -221,6 +221,7 @@ def _generate_null_hocr(output_hocr, output_text, image):
 
 
 def generate_hocr(
+    *,
     input_file: Path,
     output_hocr: Path,
     output_text: Path,

src/ocrmypdf/_exec/unpaper.py

@@ -69,7 +69,7 @@ def _setup_unpaper_io(tmpdir: Path, input_file: Path) -> Tuple[Path, Path]:
 
 
 def run(
-    input_file: Path, output_file: Path, dpi: DecFloat, mode_args: List[str]
+    input_file: Path, output_file: Path, *, dpi: DecFloat, mode_args: List[str]
 ) -> None:
     args_unpaper = ['unpaper', '-v', '--dpi', str(round(dpi, 6))] + mode_args
 
@@ -114,6 +114,7 @@ def validate_custom_args(args: str) -> List[str]:
 def clean(
     input_file: Path,
     output_file: Path,
+    *,
     dpi: DecFloat,
     unpaper_args: Optional[List[str]] = None,
 ):
@@ -130,4 +131,4 @@ def clean(
     ]
     if not unpaper_args:
         unpaper_args = default_args
-    run(input_file, output_file, dpi, unpaper_args)
+    run(input_file, output_file, dpi=dpi, mode_args=unpaper_args)

src/ocrmypdf/_graft.py

@@ -6,22 +6,31 @@
 
 
 import logging
+import uuid
 from contextlib import suppress
 from pathlib import Path
 from typing import Optional
 
 import pikepdf
+from pikepdf.objects import Dictionary, Name
 
 log = logging.getLogger(__name__)
 MAX_REPLACE_PAGES = 100
 
 
-def _update_page_resources(*, page, font, font_key, procset):
-    """Update this page's fonts with a reference to the Glyphless font"""
+def _ensure_dictionary(obj, name):
+    if name not in obj:
+        obj[name] = pikepdf.Dictionary({})
+    return obj[name]
 
-    if '/Resources' not in page:
-        page['/Resources'] = pikepdf.Dictionary({})
-    resources = page['/Resources']
+
+def _update_resources(*, obj, font, font_key, procset):
+    """Update this obj's fonts with a reference to the Glyphless font.
+
+    obj can be a page or Form XObject.
+    """
+
+    resources = _ensure_dictionary(obj, '/Resources')
     try:
         fonts = resources['/Font']
     except KeyError:
@@ -32,7 +41,8 @@ def _update_page_resources(*, page, font, font_key, procset):
 
     # Reassign /ProcSet to one that just lists everything - ProcSet is
     # obsolete and doesn't matter but recommended for old viewer support
-    resources['/ProcSet'] = procset
+    if procset:
+        resources['/ProcSet'] = procset
 
 
 def strip_invisible_text(pdf, page):
@@ -169,13 +179,13 @@ class OcrGrafter:
         """
 
         page0 = self.pdf_base.pages[0]
-        _update_page_resources(
-            page=page0, font=self.font, font_key=self.font_key, procset=self.procset
+        _update_resources(
+            obj=page0, font=self.font, font_key=self.font_key, procset=self.procset
         )
 
         # We cannot read and write the same file, that will corrupt it
         # but we don't to keep more copies than we need to. Delete intermediates.
-        # {interim_count} is the opened file we were updateing
+        # {interim_count} is the opened file we were updating
         # {interim_count - 1} can be deleted
         # {interim_count + 1} is the new file will produce and open
         old_file = self.output_file.with_suffix(f'.working{self.interim_count - 1}.pdf')
@@ -210,6 +220,7 @@ class OcrGrafter:
                     pdf_text_fonts = pdf_text.pages[0].Resources.get('/Font', {})
                 except (AttributeError, IndexError, KeyError):
                     return None, None
+                pdf_text_font = None
                 for f in possible_font_names:
                     pdf_text_font = pdf_text_fonts.get(f, None)
                     if pdf_text_font is not None:
@@ -279,17 +290,29 @@ class OcrGrafter:
             # finally move the lower left corner to match the mediabox
             ctm = translate @ rotate @ scale @ untranslate @ corner
 
-            pdf_text_contents = (
-                b'q %s cm\n' % ctm.encode() + pdf_text_contents + b'\nQ\n'
+            base_resources = _ensure_dictionary(base_page, '/Resources')
+            base_xobjs = _ensure_dictionary(base_resources, '/XObject')
+            text_xobj_name = Name('/' + str(uuid.uuid4()))
+            xobj = self.pdf_base.make_stream(pdf_text_contents)
+            base_xobjs[text_xobj_name] = xobj
+            xobj.Type = Name.XObject
+            xobj.Subtype = Name.Form
+            xobj.FormType = 1
+            xobj.BBox = mediabox
+            _update_resources(
+                obj=xobj, font=font, font_key=font_key, procset=[Name.PDF]
             )
 
-            new_text_layer = pikepdf.Stream(self.pdf_base, pdf_text_contents)
+            pdf_draw_xobj = (
+                (b'q %s cm\n' % ctm.encode()) + (b'%s Do\n' % text_xobj_name) + b'\nQ\n'
+            )
+            new_text_layer = pikepdf.Stream(self.pdf_base, pdf_draw_xobj)
 
             if strip_old_text:
                 strip_invisible_text(self.pdf_base, base_page)
 
             base_page.page_contents_add(new_text_layer, prepend=True)
 
-            _update_page_resources(
-                page=base_page, font=font, font_key=font_key, procset=procset
+            _update_resources(
+                obj=base_page, font=font, font_key=font_key, procset=procset
             )

src/ocrmypdf/_pipeline.py

@@ -483,7 +483,12 @@ def preprocess_deskew(input_file: Path, page_context: PageContext):
 def preprocess_clean(input_file: Path, page_context: PageContext):
     output_file = page_context.get_path('pp_clean.png')
     dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
-    unpaper.clean(input_file, output_file, dpi.x, page_context.options.unpaper_args)
+    unpaper.clean(
+        input_file,
+        output_file,
+        dpi=dpi.x,
+        unpaper_args=page_context.options.unpaper_args,
+    )
     return output_file
 
 
@@ -627,9 +632,9 @@ def render_hocr_page(hocr: Path, page_context: PageContext):
     dpi = get_page_square_dpi(page_context.pageinfo, options)
     debug_mode = options.pdf_renderer == 'hocrdebug'
 
-    hocrtransform = HocrTransform(hocr, dpi.x)  # square
+    hocrtransform = HocrTransform(hocr_filename=hocr, dpi=dpi.x)  # square
     hocrtransform.to_pdf(
-        output_file,
+        out_filename=output_file,
         image_filename=None,
         show_bounding_boxes=False if not debug_mode else True,
         invisible_text=True if not debug_mode else False,

src/ocrmypdf/api.py

@@ -48,6 +48,7 @@ class Verbosity(IntEnum):
 
 def configure_logging(
     verbosity: Verbosity,
+    *,
     progress_bar_friendly: bool = True,
     manage_root_logger: bool = False,
     plugin_manager=None,

src/ocrmypdf/hocrtransform.py

@@ -77,7 +77,7 @@ class HocrTransform:
         {'ff': 'ff', 'ffi': 'f‌f‌i', 'ffl': 'f‌f‌l', 'fi': 'fi', 'fl': 'fl'}
     )
 
-    def __init__(self, hocr_filename: Union[str, Path], dpi: float):
+    def __init__(self, *, hocr_filename: Union[str, Path], dpi: float):
         self.dpi = dpi
         self.hocr = ElementTree.parse(os.fspath(hocr_filename))
 
@@ -182,6 +182,7 @@ class HocrTransform:
 
     def to_pdf(
         self,
+        *,
         out_filename: Path,
         image_filename: Optional[Path] = None,
         show_bounding_boxes: bool = False,
@@ -433,10 +434,10 @@ if __name__ == "__main__":
     parser.add_argument('outputfile', help='Path to the PDF file to be generated')
     args = parser.parse_args()
 
-    hocr = HocrTransform(args.hocrfile, args.resolution)
+    hocr = HocrTransform(hocr_filename=args.hocrfile, dpi=args.resolution)
     hocr.to_pdf(
-        args.outputfile,
-        args.image,
-        args.boundingboxes,
+        out_filename=args.outputfile,
+        image_filename=args.image,
+        show_bounding_boxes=args.boundingboxes,
         interword_spaces=args.interword_spaces,
     )

src/ocrmypdf/optimize.py

@@ -34,7 +34,7 @@ from ocrmypdf._concurrent import Executor, SerialExecutor
 from ocrmypdf._exec import jbig2enc, pngquant
 from ocrmypdf._jobcontext import PdfContext
 from ocrmypdf.exceptions import OutputFileAccessError
-from ocrmypdf.helpers import deprecated, safe_symlink
+from ocrmypdf.helpers import safe_symlink
 
 log = logging.getLogger(__name__)
 
@@ -62,10 +62,6 @@ def jpg_name(root: Path, xref: Xref) -> Path:
     return img_name(root, xref, '.jpg')
 
 
-def tif_name(root: Path, xref: Xref) -> Path:
-    return img_name(root, xref, '.tif')
-
-
 def extract_image_filter(
     pike: Pdf, root: Path, image: Object, xref: Xref
 ) -> Optional[Tuple[PdfImage, Tuple[Name, Object]]]:
@@ -523,81 +519,6 @@ def transcode_pngs(
         _transcode_png(pike, filename, xref)
 
 
-@deprecated
-def rewrite_png_as_g4(pike: Pdf, im_obj: Object, compdata) -> None:  # pragma: no cover
-    im_obj.BitsPerComponent = 1
-    im_obj.Width = compdata.w
-    im_obj.Height = compdata.h
-
-    im_obj.write(compdata.read())
-
-    log.debug(f"PNG to G4 {im_obj.objgen}")
-    if Name.Predictor in im_obj:
-        del im_obj.Predictor
-    if Name.DecodeParms in im_obj:
-        del im_obj.DecodeParms
-    im_obj.DecodeParms = Dictionary(
-        K=-1, BlackIs1=bool(compdata.minisblack), Columns=compdata.w
-    )
-
-    im_obj.Filter = Name.CCITTFaxDecode
-    return
-
-
-@deprecated
-def rewrite_png(pike: Pdf, im_obj: Object, compdata) -> None:  # pragma: no cover
-    # When a PNG is inserted into a PDF, we more or less copy the IDAT section from
-    # the PDF and transfer the rest of the PNG headers to PDF image metadata.
-    # One thing we have to do is tell the PDF reader whether a predictor was used
-    # on the image before Flate encoding. (Typically one is.)
-    # According to Leptonica source, PDF readers don't actually need us
-    # to specify the correct predictor, they just need a value of either:
-    #   1 - no predictor
-    #   10-14 - there is a predictor
-    # Leptonica's compdata->predictor only tells TRUE or FALSE
-    # 10-14 means the actual predictor is specified in the data, so for any
-    # number >= 10 the PDF reader will use whatever the PNG data specifies.
-    # In practice Leptonica should use Paeth, 14, but 15 seems to be the
-    # designated value for "optimal". So we will use 15.
-    # See:
-    #   - PDF RM 7.4.4.4 Table 10
-    #   - https://github.com/DanBloomberg/leptonica/blob/master/src/pdfio2.c#L757
-    predictor = 15 if compdata.predictor > 0 else 1
-    dparms = Dictionary(Predictor=predictor)
-    if predictor > 1:
-        dparms.BitsPerComponent = compdata.bps  # Yes, this is redundant
-        dparms.Colors = compdata.spp
-        dparms.Columns = compdata.w
-
-    im_obj.BitsPerComponent = compdata.bps
-    im_obj.Width = compdata.w
-    im_obj.Height = compdata.h
-
-    log.debug(
-        f"PNG {im_obj.objgen}: palette={compdata.ncolors} spp={compdata.spp} bps={compdata.bps}"
-    )
-    if compdata.ncolors > 0:
-        # .ncolors is the number of colors in the palette, not the number of
-        # colors used in a true color image. The palette string is always
-        # given as RGB tuples even when the image is grayscale; see
-        # https://github.com/DanBloomberg/leptonica/blob/master/src/colormap.c#L2067
-        palette_pdf_string = compdata.get_palette_pdf_string()
-        palette_data = pikepdf.Object.parse(palette_pdf_string)
-        palette_stream = pikepdf.Stream(pike, bytes(palette_data))
-        palette = [Name.Indexed, Name.DeviceRGB, compdata.ncolors - 1, palette_stream]
-        cs = palette
-    else:
-        # ncolors == 0 means we are using a colorspace without a palette
-        if compdata.spp == 1:
-            cs = Name.DeviceGray
-        elif compdata.spp == 4:
-            cs = Name.DeviceCMYK
-        else:  # spp == 3
-            cs = Name.DeviceRGB
-    im_obj.ColorSpace = cs
-    im_obj.write(compdata.read(), filter=Name.FlateDecode, decode_parms=dparms)
-
-
 def optimize(
     input_file: Path,
     output_file: Path,

tests/cache/manifest.jsonl

@@ -1,64 +1,44 @@
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__deu__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/francais.pdf", "args": ["-l", "deu", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/2400dpi.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/graph_ocred.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000005_ocr.png__000005_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000005_ocr.png", "$TMPDIR/000005_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000005_ocr.png__000005_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000005_ocr.png", "$TMPDIR/000005_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000005_ocr.png__000005_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000005_ocr.png", "$TMPDIR/000005_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000005_ocr.png__000005_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000005_ocr.png", "$TMPDIR/000005_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000006_ocr.png__000006_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000006_ocr.png", "$TMPDIR/000006_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000006_ocr.png__000006_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000006_ocr.png", "$TMPDIR/000006_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000006_ocr.png__000006_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000006_ocr.png", "$TMPDIR/000006_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000006_ocr.png__000006_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000006_ocr.png", "$TMPDIR/000006_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/lichtenstein.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/lichtenstein.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000006_ocr.png__000006_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000006_ocr.png", "$TMPDIR/000006_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/aspect.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__osd__--psm__0__000001_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001_rasterize_preview.jpg", "stdout"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__osd__--psm__0__000003_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000003_rasterize_preview.jpg", "stdout"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__osd__--psm__0__000004_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000004_rasterize_preview.jpg", "stdout"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__osd__--psm__0__000002_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000002_rasterize_preview.jpg", "stdout"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/aspect.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__osd__--psm__0__000004_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000004_rasterize_preview.jpg", "stdout"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__osd__--psm__0__000001_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001_rasterize_preview.jpg", "stdout"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__osd__--psm__0__000003_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000003_rasterize_preview.jpg", "stdout"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__osd__--psm__0__000002_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000002_rasterize_preview.jpg", "stdout"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__--psm__7__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "--psm", "7", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_hocr", "hocr", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__--psm__7__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "--psm", "7", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_tess", "pdf", "txt"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__osd__--psm__0__000001_rasterize_preview.jpg__stdout", "sourcefile": "resources/poster.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001_rasterize_preview.jpg", "stdout"]}
-{"tesseract_version": "4.1.1", "platform": "Darwin-18.7.0-x86_64-i386-64bit", "python": "3.7.7", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__deu__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/francais.pdf", "args": ["-l", "deu", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__--psm__7__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "--psm", "7", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__--psm__7__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "--psm", "7", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/aspect.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/lichtenstein.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_hocr__hocr__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/2400dpi.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/aspect.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/ccitt.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/graph_ocred.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/jbig2.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/lichtenstein.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/palette.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/poster.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/skew.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000002_ocr.png__000002_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000002_ocr.png", "$TMPDIR/000002_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/3small.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000003_ocr.png__000003_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000003_ocr.png", "$TMPDIR/000003_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000004_ocr.png__000004_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000004_ocr.png", "$TMPDIR/000004_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000005_ocr.png__000005_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000005_ocr.png", "$TMPDIR/000005_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000005_ocr.png__000005_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000005_ocr.png", "$TMPDIR/000005_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000006_ocr.png__000006_ocr_hocr__hocr__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "$TMPDIR/000006_ocr.png", "$TMPDIR/000006_ocr_hocr", "hocr", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__eng__000006_ocr.png__000006_ocr_tess__pdf__txt", "sourcefile": "resources/multipage.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000006_ocr.png", "$TMPDIR/000006_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__osd__--psm__0__000001_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__osd__--psm__0__000001_rasterize_preview.jpg__stdout", "sourcefile": "resources/poster.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000001_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__osd__--psm__0__000002_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000002_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__osd__--psm__0__000003_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000003_rasterize_preview.jpg", "stdout"]}
+{"tesseract_version": "4.1.1", "platform": "macOS-10.14.6-x86_64-i386-64bit", "python": "3.9.0", "argv_slug": "__-l__osd__--psm__0__000004_rasterize_preview.jpg__stdout", "sourcefile": "resources/cardinal.pdf", "args": ["-l", "osd", "--psm", "0", "$TMPDIR/000004_rasterize_preview.jpg", "stdout"]}

tests/test_hocrtransform.py

@@ -53,8 +53,10 @@ def test_mono_image(blank_hocr, outdir):
         im.putpixel((n, n), 1)
     im.save(outdir / 'mono.tif', format='TIFF')
 
-    hocr = hocrtransform.HocrTransform(str(blank_hocr), 300)
-    hocr.to_pdf(str(outdir / 'mono.pdf'), image_filename=str(outdir / 'mono.tif'))
+    hocr = hocrtransform.HocrTransform(hocr_filename=str(blank_hocr), dpi=300)
+    hocr.to_pdf(
+        out_filename=str(outdir / 'mono.pdf'), image_filename=str(outdir / 'mono.tif')
+    )
 
     check_pdf(str(outdir / 'mono.pdf'))
 

tests/test_optimize.py

@@ -143,7 +143,7 @@ def test_multiple_pngs(resources, outdir):
             outputstream=inpdf,
         )
 
-    def mockquant(input_file, output_file, _quality_min, _quality_max):
+    def mockquant(input_file, output_file, *args):
         with Image.open(input_file) as im:
             draw = ImageDraw.Draw(im)
             draw.rectangle((0, 0, im.width, im.height), fill=128)