pdfinfo: replace most remaining dict-style access

ocrmypdf/__main__.py

@@ -734,7 +734,7 @@ def run_pipeline():
                  180: 's', 270: 'w'}
     orientations = []
     for n, page in enumerate(pdfinfo):
-        angle = pdfinfo[n].get('rotated', 0)
+        angle = pdfinfo[n].rotation or 0
         if angle != 0:
             orientations.append('{0}{1}'.format(
                 n + 1,

ocrmypdf/pdfinfo.py

@@ -592,14 +592,14 @@ def _pdf_get_pageinfo(pdf, pageno: int):
     return pageinfo
 
 
-def pdf_get_all_pageinfo(infile):
+def _pdf_get_all_pageinfo(infile):
     if isinstance(infile, Path):
         infile = str(infile)
     pdf = pypdf.PdfFileReader(infile)
     return [PageInfo(pdf, n) for n in range(pdf.numPages)]
 
 
-class PageInfo(MutableMapping):
+class PageInfo:
     def __init__(self, infile, pageno):
         self._infile = infile
         self._pageno = pageno
@@ -631,7 +631,14 @@ class PageInfo(MutableMapping):
 
     @property
     def rotation(self):
-        return self._pageinfo['rotate']
+        return self._pageinfo.get('rotate', None)
+
+    @rotation.setter
+    def rotation(self, value):
+        if value in (0, 90, 180, 270, 360, -90, -180, -270):
+            self._pageinfo['rotate'] = value
+        else:
+            raise ValueError("rotation must be a cardinal angle")
 
     @property
     def images(self):
@@ -645,27 +652,21 @@ class PageInfo(MutableMapping):
     def yres(self):
         return self._pageinfo.get('yres', None)
 
+    @property
+    def userunit(self):
+        return self._pageinfo.get('userunit', None)
+
+    @property
+    def min_version(self):
+        if self.userunit is not None:
+            return '1.6'
+        else:
+            return '1.5'
+
     @property
     def images(self):
         return self._pageinfo['images']
 
-    def __getitem__(self, item):
-        warnings.warn("pageinfo[item] is deprecated", DeprecationWarning)
-        return self._pageinfo[item]
-
-    def __len__(self):
-        return len(self._pageinfo)
-
-    def __iter__(self):
-        return iter(self._pageinfo)
-
-    def __setitem__(self, key, value):
-        warnings.warn("pageinfo[item] is deprecated", DeprecationWarning)
-        self._pageinfo[key] = value
-
-    def __delitem__(self, key):
-        del self._pageinfo[key]
-
     def __repr__(self):
         return (
             '<PageInfo '
@@ -677,13 +678,21 @@ class PageInfo(MutableMapping):
 
 
 class PdfInfo:
+    """Get summary information about a PDF
+    
+    """
     def __init__(self, infile):
-        self._pages = pdf_get_all_pageinfo(infile)
+        self._pages = _pdf_get_all_pageinfo(infile)
 
     @property
     def pages(self):
         return self._pages
 
+    @property
+    def min_version(self):
+        # The minimum PDF is the maximum version that any particular page needs
+        return max(page.min_version for page in self.pages)
+
     def __getitem__(self, item):
         return self._pages[item]
 
@@ -699,7 +708,7 @@ def main():
     parser = argparse.ArgumentParser()
     parser.add_argument('infile')
     args = parser.parse_args()
-    info = pdf_get_all_pageinfo(args.infile)
+    info = _pdf_get_all_pageinfo(args.infile)
     from pprint import pprint
     pprint(info)
 

ocrmypdf/pipeline.py

@@ -196,16 +196,16 @@ def get_pageinfo(input_file, context):
 
 def get_page_dpi(pageinfo, options):
     "Get the DPI when nonsquare DPI is tolerable"
-    xres = max(pageinfo.get('xres', VECTOR_PAGE_DPI), options.oversample or 0)
-    yres = max(pageinfo.get('yres', VECTOR_PAGE_DPI), options.oversample or 0)
+    xres = max(pageinfo.xres or VECTOR_PAGE_DPI, options.oversample or 0)
+    yres = max(pageinfo.yres or VECTOR_PAGE_DPI, options.oversample or 0)
     return (float(xres), float(yres))
 
 
 def get_page_square_dpi(pageinfo, options):
     "Get the DPI when we require xres == yres"
     return float(max(
-        pageinfo.get('xres', VECTOR_PAGE_DPI),
-        pageinfo.get('yres', VECTOR_PAGE_DPI),
+        pageinfo.xres or VECTOR_PAGE_DPI,
+        pageinfo.yres or VECTOR_PAGE_DPI,
         options.oversample or 0))
 
 
@@ -383,7 +383,7 @@ def orient_page(
 
         pageno = int(os.path.basename(page_pdf)[0:6]) - 1
         pdfinfo = context.get_pdfinfo()
-        pdfinfo[pageno]['rotated'] = orient_conf.angle
+        pdfinfo[pageno].rotation = orient_conf.angle
         context.set_pdfinfo(pdfinfo)
 
 

tests/conftest.py

@@ -132,4 +132,4 @@ def first_page_dimensions(pdf):
     from ocrmypdf import pdfinfo
     info = pdfinfo.PdfInfo(pdf)
     page0 = info[0]
-    return (page0['width_inches'], page0['height_inches'])
+    return (page0.width_inches, page0.height_inches)

tests/test_pageinfo.py

@@ -28,10 +28,10 @@ def test_single_page_text(outdir):
     pdf.showPage()
     pdf.save()
 
-    pdfinfo = pdfinfo.PdfInfo(filename)
+    info = pdfinfo.PdfInfo(filename)
 
-    assert len(pdfinfo) == 1
-    page = pdfinfo[0]
+    assert len(info) == 1
+    page = info[0]
 
     assert page.has_text
     assert len(page.images) == 0
@@ -55,10 +55,10 @@ def test_single_page_image(outdir):
             layout_fun=layout_fun)
     filename.write_bytes(pdf_bytes)
 
-    pdfinfo = pdfinfo.PdfInfo(filename)
+    info = pdfinfo.PdfInfo(filename)
 
-    assert len(pdfinfo) == 1
-    page = pdfinfo[0]
+    assert len(info) == 1
+    page = info[0]
 
     assert not page.has_text
     assert len(page.images) == 1
@@ -85,9 +85,9 @@ def test_single_page_inline_image(outdir):
         pdf.showPage()
         pdf.save()
 
-    pdfinfo = pdfinfo.PdfInfo(filename)
-    print(pdfinfo)
-    pdfimage = pdfinfo[0].images[0]
+    pdf = pdfinfo.PdfInfo(filename)
+    print(pdf)
+    pdfimage = pdf[0].images[0]
     assert isclose(pdfimage.xres, 8)
     assert pdfimage.color == Colorspace.rgb  # reportlab produces color image
     assert pdfimage.width == 8
@@ -96,9 +96,9 @@ def test_single_page_inline_image(outdir):
 def test_jpeg(resources, outdir):
     filename = resources / 'c02-22.pdf'
 
-    pdfinfo = pdfinfo.PdfInfo(filename)
+    pdf = pdfinfo.PdfInfo(filename)
 
-    pdfimage = pdfinfo[0].images[0]
+    pdfimage = pdf[0].images[0]
     assert pdfimage.enc == Encoding.jpeg
     assert isclose(pdfimage.xres, 150)
 
@@ -106,14 +106,14 @@ def test_jpeg(resources, outdir):
 def test_form_xobject(resources):
     filename = resources / 'formxobject.pdf'
 
-    pdfinfo = pdfinfo.PdfInfo(filename)
-    pdfimage = pdfinfo[0].images[0]
+    pdf = pdfinfo.PdfInfo(filename)
+    pdfimage = pdf[0].images[0]
     assert pdfimage.width == 50
 
 
 def test_no_contents(resources):
     filename = resources / 'no_contents.pdf'
 
-    pdfinfo = pdfinfo.PdfInfo(filename)
-    assert len(pdfinfo[0].images) == 0
-    assert pdfinfo[0].has_text == False
+    pdf = pdfinfo.PdfInfo(filename)
+    assert len(pdf[0].images) == 0
+    assert pdf[0].has_text == False