Refactor PdfInfo(str(filename)) -> PdfInfo(filename)

ocrmypdf/pageinfo.py

@@ -9,6 +9,7 @@ import sys
 import PyPDF2 as pypdf
 from collections import namedtuple
 import warnings
+from pathlib import Path
 
 
 matrix_mult = pypdf.pdf.utils.matrixMultiply
@@ -517,6 +518,8 @@ def _pdf_get_pageinfo(infile, pageno: int):
 
 
 def pdf_get_all_pageinfo(infile):
+    if isinstance(infile, Path):
+        infile = str(infile)
     pdf = pypdf.PdfFileReader(infile)
     return [_pdf_get_pageinfo(infile, n) for n in range(pdf.numPages)]
 

tests/conftest.py

@@ -130,6 +130,6 @@ def run_ocrmypdf(input_file, output_file, *args, env=None):
 @pytest.helpers.register
 def first_page_dimensions(pdf):
     from ocrmypdf import pageinfo
-    info = pageinfo.pdf_get_all_pageinfo(str(pdf))
+    info = pageinfo.PdfInfo(pdf)
     page0 = info[0]
     return (page0['width_inches'], page0['height_inches'])

tests/test_main.py

@@ -230,7 +230,7 @@ def test_oversample(spoof_tesseract_cache, renderer, resources, outpdf):
         '-f',
         '--pdf-renderer', renderer, env=spoof_tesseract_cache)
 
-    pdfinfo = PdfInfo(str(oversampled_pdf))
+    pdfinfo = PdfInfo(oversampled_pdf)
 
     print(pdfinfo[0]['xres'])
     assert abs(pdfinfo[0]['xres'] - 350) < 1
@@ -358,14 +358,14 @@ def test_autorotate_threshold(
 def test_ocr_timeout(renderer, resources, outpdf):
     out = check_ocrmypdf(resources / 'skew.pdf', outpdf,
                          '--tesseract-timeout', '1.0')
-    pdfinfo = PdfInfo(str(out))
+    pdfinfo = PdfInfo(out)
     assert not pdfinfo[0]['has_text']
 
 
 def test_skip_big(spoof_tesseract_cache, resources, outpdf):
     out = check_ocrmypdf(resources / 'enormous.pdf', outpdf,
                          '--skip-big', '10', env=spoof_tesseract_cache)
-    pdfinfo = PdfInfo(str(out))
+    pdfinfo = PdfInfo(out)
     assert not pdfinfo[0]['has_text']
 
 
@@ -562,14 +562,14 @@ def test_algo4(resources, no_outpdf):
 def test_non_square_resolution(renderer, spoof_tesseract_cache,
                                resources, outpdf):
     # Confirm input image is non-square resolution
-    in_pageinfo = PdfInfo(str(resources / 'aspect.pdf'))
+    in_pageinfo = PdfInfo(resources / 'aspect.pdf')
     assert in_pageinfo[0]['xres'] != in_pageinfo[0]['yres']
 
     check_ocrmypdf(
         resources / 'aspect.pdf', outpdf,
         '--pdf-renderer', renderer, env=spoof_tesseract_cache)
 
-    out_pageinfo = PdfInfo(str(outpdf))
+    out_pageinfo = PdfInfo(outpdf)
 
     # Confirm resolution was kept the same
     assert in_pageinfo[0]['xres'] == out_pageinfo[0]['xres']
@@ -585,7 +585,7 @@ def test_convert_to_square_resolution(renderer, spoof_tesseract_cache,
     from math import isclose
 
     # Confirm input image is non-square resolution
-    in_pageinfo = PdfInfo(str(resources / 'aspect.pdf'))
+    in_pageinfo = PdfInfo(resources / 'aspect.pdf')
     assert in_pageinfo[0]['xres'] != in_pageinfo[0]['yres']
 
     # --force-ocr requires means forced conversion to square resolution
@@ -594,7 +594,7 @@ def test_convert_to_square_resolution(renderer, spoof_tesseract_cache,
         '--force-ocr',
         '--pdf-renderer', renderer, env=spoof_tesseract_cache)
 
-    out_pageinfo = PdfInfo(str(outpdf))
+    out_pageinfo = PdfInfo(outpdf)
 
     in_p0, out_p0 = in_pageinfo[0], out_pageinfo[0]
 
@@ -628,7 +628,7 @@ def test_jbig2_passthrough(spoof_tesseract_cache, resources, outpdf):
         '--pdf-renderer', 'hocr',
         env=spoof_tesseract_cache)
 
-    out_pageinfo = PdfInfo(str(out))
+    out_pageinfo = PdfInfo(out)
     assert out_pageinfo[0]['images'][0]['enc'] == 'jbig2'
 
 
@@ -713,7 +713,7 @@ def test_rotated_skew_timeout(resources, outpdf):
         '--pdf-renderer', 'hocr',
         '--deskew', '--tesseract-timeout', '0')
 
-    out_pageinfo = PdfInfo(str(out))[0]
+    out_pageinfo = PdfInfo(out)[0]
 
     assert out_pageinfo['height_pixels'] > out_pageinfo['width_pixels'], \
         "Expected the output page to be portrait"
@@ -970,7 +970,7 @@ def test_sidecar_pagecount(spoof_tesseract_cache, resources, outpdf):
         '--sidecar', sidecar,
         env=spoof_tesseract_cache)
 
-    pdfinfo = PdfInfo(str(resources / 'multipage.pdf'))
+    pdfinfo = PdfInfo(resources / 'multipage.pdf')
     num_pages = len(pdfinfo)
 
     with open(sidecar, 'r') as f:

tests/test_pageinfo.py

@@ -26,7 +26,7 @@ def test_single_page_text(outdir):
     pdf.showPage()
     pdf.save()
 
-    pdfinfo = pageinfo.PdfInfo(str(filename))
+    pdfinfo = pageinfo.PdfInfo(filename)
 
     assert len(pdfinfo) == 1
     page = pdfinfo[0]
@@ -53,7 +53,7 @@ def test_single_page_image(outdir):
             layout_fun=layout_fun)
     filename.write_bytes(pdf_bytes)
 
-    pdfinfo = pageinfo.PdfInfo(str(filename))
+    pdfinfo = pageinfo.PdfInfo(filename)
 
     assert len(pdfinfo) == 1
     page = pdfinfo[0]
@@ -83,7 +83,7 @@ def test_single_page_inline_image(outdir):
         pdf.showPage()
         pdf.save()
 
-    pdfinfo = pageinfo.PdfInfo(str(filename))
+    pdfinfo = pageinfo.PdfInfo(filename)
     print(pdfinfo)
     pdfimage = pdfinfo[0]['images'][0]
     assert (pdfimage['dpi_w'] - 8) < 1e-5
@@ -94,7 +94,7 @@ def test_single_page_inline_image(outdir):
 def test_jpeg(resources, outdir):
     filename = resources / 'c02-22.pdf'
 
-    pdfinfo = pageinfo.PdfInfo(str(filename))
+    pdfinfo = pageinfo.PdfInfo(filename)
 
     pdfimage = pdfinfo[0]['images'][0]
     assert pdfimage['enc'] == 'jpeg'
@@ -104,7 +104,7 @@ def test_jpeg(resources, outdir):
 def test_form_xobject(resources):
     filename = resources / 'formxobject.pdf'
 
-    pdfinfo = pageinfo.PdfInfo(str(filename))
+    pdfinfo = pageinfo.PdfInfo(filename)
     pdfimage = pdfinfo[0]['images'][0]
     assert pdfimage['width'] == 50
 
@@ -112,6 +112,6 @@ def test_form_xobject(resources):
 def test_no_contents(resources):
     filename = resources / 'no_contents.pdf'
 
-    pdfinfo = pageinfo.PdfInfo(str(filename))
+    pdfinfo = pageinfo.PdfInfo(filename)
     assert len(pdfinfo[0]['images']) == 0
     assert pdfinfo[0]['has_text'] == False

tests/test_tess4.py

@@ -96,9 +96,9 @@ def test_skip_pages_does_not_replicate(
         env=ensure_tess4
     )
 
-    info_in = pageinfo.pdf_get_all_pageinfo(str(infile))
+    info_in = pageinfo.PdfInfo(infile)
 
-    info = pageinfo.pdf_get_all_pageinfo(str(outpdf))
+    info = pageinfo.PdfInfo(outpdf)
     for page in info:
         assert len(page['images']) == 1, "skipped page was replicated"
 
@@ -115,6 +115,6 @@ def test_content_preservation(ensure_tess4, resources, outpdf):
         env=ensure_tess4
     )
 
-    info = pageinfo.pdf_get_all_pageinfo(str(outpdf))
+    info = pageinfo.PdfInfo(outpdf)
     page = info[0]
     assert len(page['images']) > 1, "masked were rasterized"