Rename pageinfo to pdfinfo

ocrmypdf/pipeline.py

@@ -22,7 +22,7 @@ from PIL import Image
 from ruffus import formatter, regex, Pipeline, suffix
 
 from .hocrtransform import HocrTransform
-from .pageinfo import PdfInfo, Encoding, Colorspace
+from .pdfinfo import PdfInfo, Encoding, Colorspace
 from .pdfa import generate_pdfa_ps, file_claims_pdfa
 from .helpers import re_symlink, is_iterable_notstr, page_number
 from .exec import ghostscript, tesseract, qpdf

tests/conftest.py

@@ -129,7 +129,7 @@ def run_ocrmypdf(input_file, output_file, *args, env=None):
 
 @pytest.helpers.register
 def first_page_dimensions(pdf):
-    from ocrmypdf import pageinfo
-    info = pageinfo.PdfInfo(pdf)
+    from ocrmypdf import pdfinfo
+    info = pdfinfo.PdfInfo(pdf)
     page0 = info[0]
     return (page0['width_inches'], page0['height_inches'])

tests/test_main.py

@@ -5,7 +5,7 @@ from subprocess import Popen, PIPE, check_output, check_call, DEVNULL
 import os
 import shutil
 import pytest
-from ocrmypdf.pageinfo import PdfInfo, Colorspace, Encoding
+from ocrmypdf.pdfinfo import PdfInfo, Colorspace, Encoding
 import PyPDF2 as pypdf
 from ocrmypdf.exceptions import ExitCode
 from ocrmypdf import leptonica

tests/test_pageinfo.py

@@ -1,12 +1,12 @@
 #!/usr/bin/env python3
 # © 2015 James R. Barlow: github.com/jbarlow83
 
-from ocrmypdf import pageinfo
+from ocrmypdf import pdfinfo
 from reportlab.pdfgen.canvas import Canvas
 from PIL import Image
 from tempfile import NamedTemporaryFile
 from math import isclose
-from ocrmypdf.pageinfo import Colorspace, Encoding
+from ocrmypdf.pdfinfo import Colorspace, Encoding
 from contextlib import suppress
 import os
 import shutil
@@ -28,7 +28,7 @@ def test_single_page_text(outdir):
     pdf.showPage()
     pdf.save()
 
-    pdfinfo = pageinfo.PdfInfo(filename)
+    pdfinfo = pdfinfo.PdfInfo(filename)
 
     assert len(pdfinfo) == 1
     page = pdfinfo[0]
@@ -55,7 +55,7 @@ def test_single_page_image(outdir):
             layout_fun=layout_fun)
     filename.write_bytes(pdf_bytes)
 
-    pdfinfo = pageinfo.PdfInfo(filename)
+    pdfinfo = pdfinfo.PdfInfo(filename)
 
     assert len(pdfinfo) == 1
     page = pdfinfo[0]
@@ -85,7 +85,7 @@ def test_single_page_inline_image(outdir):
         pdf.showPage()
         pdf.save()
 
-    pdfinfo = pageinfo.PdfInfo(filename)
+    pdfinfo = pdfinfo.PdfInfo(filename)
     print(pdfinfo)
     pdfimage = pdfinfo[0].images[0]
     assert isclose(pdfimage.xres, 8)
@@ -96,7 +96,7 @@ def test_single_page_inline_image(outdir):
 def test_jpeg(resources, outdir):
     filename = resources / 'c02-22.pdf'
 
-    pdfinfo = pageinfo.PdfInfo(filename)
+    pdfinfo = pdfinfo.PdfInfo(filename)
 
     pdfimage = pdfinfo[0].images[0]
     assert pdfimage.enc == Encoding.jpeg
@@ -106,7 +106,7 @@ def test_jpeg(resources, outdir):
 def test_form_xobject(resources):
     filename = resources / 'formxobject.pdf'
 
-    pdfinfo = pageinfo.PdfInfo(filename)
+    pdfinfo = pdfinfo.PdfInfo(filename)
     pdfimage = pdfinfo[0].images[0]
     assert pdfimage.width == 50
 
@@ -114,6 +114,6 @@ def test_form_xobject(resources):
 def test_no_contents(resources):
     filename = resources / 'no_contents.pdf'
 
-    pdfinfo = pageinfo.PdfInfo(filename)
+    pdfinfo = pdfinfo.PdfInfo(filename)
     assert len(pdfinfo[0].images) == 0
     assert pdfinfo[0].has_text == False

tests/test_tess4.py

@@ -4,7 +4,7 @@
 import pytest
 from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.exec import tesseract
-from ocrmypdf import pageinfo
+from ocrmypdf import pdfinfo
 import sys
 import os
 import PyPDF2 as pypdf
@@ -96,9 +96,9 @@ def test_skip_pages_does_not_replicate(
         env=ensure_tess4
     )
 
-    info_in = pageinfo.PdfInfo(infile)
+    info_in = pdfinfo.PdfInfo(infile)
 
-    info = pageinfo.PdfInfo(outpdf)
+    info = pdfinfo.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.PdfInfo(outpdf)
+    info = pdfinfo.PdfInfo(outpdf)
     page = info[0]
     assert len(page.images) > 1, "masked were rasterized"