v14.2.1 release notes

docs/release_notes.rst

@@ -28,6 +28,12 @@ tagged yet.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v14.2.1
+=======
+
+-  Fixed :issue:`977`, where images inside Form XObjects were always excluded
+   from image optimization.
+
 v14.2.0
 =======
 

pyproject.toml

@@ -37,16 +37,12 @@ classifiers = [
   "Intended Audience :: Science/Research",
   "Intended Audience :: System Administrators",
   "License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)",
-  "Operating System :: MacOS :: MacOS X",
-  "Operating System :: Microsoft :: Windows :: Windows 10",
+  "Operating System :: MacOS",
+  "Operating System :: Microsoft :: Windows",
   "Operating System :: POSIX",
   "Operating System :: POSIX :: BSD",
   "Operating System :: POSIX :: Linux",
   "Programming Language :: Python :: 3",
-  "Programming Language :: Python :: 3 :: Only",
-  "Programming Language :: Python :: 3.8",
-  "Programming Language :: Python :: 3.9",
-  "Programming Language :: Python :: 3.10",
   "Topic :: Scientific/Engineering :: Image Recognition",
   "Topic :: Text Processing :: Indexing",
   "Topic :: Text Processing :: Linguistic",

src/ocrmypdf/optimize.py

@@ -230,6 +230,65 @@ def extract_image_generic(
     return None
 
 
+def _find_image_xrefs_container(
+    pdf: Pdf,
+    container: Object,
+    pageno: int,
+    include_xrefs: MutableSet[Xref],
+    exclude_xrefs: MutableSet[Xref],
+    pageno_for_xref: dict[Xref, int],
+    depth: int = 0,
+):
+    """Find all image XRefs in a page or Form XObject and add to the include/exclude sets."""
+    if depth > 10:
+        log.warning("Recursion depth exceeded in _find_image_xrefs_page")
+        return
+    try:
+        xobjs = container.Resources.XObject
+    except AttributeError:
+        return
+    for _imname, image in dict(xobjs).items():
+        if image.objgen[1] != 0:
+            continue  # Ignore images in an incremental PDF
+        if Name.Subtype in image and image.Subtype == Name.Form:
+            # Recurse into Form XObjects
+            log.debug(f"Recursing into Form XObject {_imname} in page {pageno}")
+            _find_image_xrefs_container(
+                pdf,
+                image,
+                pageno,
+                include_xrefs,
+                exclude_xrefs,
+                pageno_for_xref,
+                depth + 1,
+            )
+            continue
+        xref = Xref(image.objgen[0])
+        if Name.SMask in image:
+            # Ignore soft masks
+            smask_xref = Xref(image.SMask.objgen[0])
+            exclude_xrefs.add(smask_xref)
+            log.debug(f"xref {smask_xref}: skipping image because it is an SMask")
+        include_xrefs.add(xref)
+        log.debug(f"xref {xref}: treating as an optimization candidate")
+        if xref not in pageno_for_xref:
+            pageno_for_xref[xref] = pageno
+
+
+def _find_image_xrefs(pdf: Pdf):
+    include_xrefs: MutableSet[Xref] = set()
+    exclude_xrefs: MutableSet[Xref] = set()
+    pageno_for_xref: dict[Xref, int] = {}
+
+    for pageno, page in enumerate(pdf.pages):
+        _find_image_xrefs_container(
+            pdf, page, pageno, include_xrefs, exclude_xrefs, pageno_for_xref
+        )
+
+    working_xrefs = include_xrefs - exclude_xrefs
+    return working_xrefs, pageno_for_xref
+
+
 def extract_images(
     pike: Pdf,
     root: Path,
@@ -250,30 +309,8 @@ def extract_images(
     it does a tuple should be returned: (xref, ext) where .ext is the file
     extension. extract_fn must also extract the file it finds interesting.
     """
-    include_xrefs: MutableSet[Xref] = set()
-    exclude_xrefs: MutableSet[Xref] = set()
-    pageno_for_xref = {}
     errors = 0
-    for pageno, page in enumerate(pike.pages):
-        try:
-            xobjs = page.Resources.XObject
-        except AttributeError:
-            continue
-        for _imname, image in dict(xobjs).items():
-            if image.objgen[1] != 0:
-                continue  # Ignore images in an incremental PDF
-            xref = Xref(image.objgen[0])
-            if Name.SMask in image:
-                # Ignore soft masks
-                smask_xref = Xref(image.SMask.objgen[0])
-                exclude_xrefs.add(smask_xref)
-                log.debug(f"xref {smask_xref}: skipping image because it is an SMask")
-            include_xrefs.add(xref)
-            log.debug(f"xref {xref}: treating as an optimization candidate")
-            if xref not in pageno_for_xref:
-                pageno_for_xref[xref] = pageno
-
-    working_xrefs = include_xrefs - exclude_xrefs
+    working_xrefs, pageno_for_xref = _find_image_xrefs(pike)
     for xref in working_xrefs:
         image = pike.get_object((xref, 0))
         try:

tests/test_optimize.py

@@ -204,3 +204,11 @@ def test_group3(resources, outdir):
         assert (
             opt.extract_image_filter(pdf, outdir, im, im.objgen[0]) is None
         ), "Group 3 should be disallowed"
+
+
+def test_find_formx(resources, outdir):
+    with pikepdf.open(resources / 'formxobject.pdf') as pdf:
+        working, pagenos = opt._find_image_xrefs(pdf)
+        assert len(working) == 1
+        xref = next(iter(working))
+        assert pagenos[xref] == 0