TST: reader.get_fields

PyPDF2/generic.py

@@ -451,7 +451,6 @@ def readStringFromStream(  # TODO: PEP8
                     tok = b""
                 else:
                     msg = rf"Unexpected escaped string: {tok.decode('utf8')}"
-                    # if.strict: PdfReadError(msg)
                     logger.warning(msg)
         txt += tok
     return createStringObject(txt, forced_encoding)

tests/test_cmap.py

@@ -38,3 +38,11 @@ def test_parse_encoding_advanced_encoding_not_implemented():
     with pytest.warns(PdfReadWarning, match="Advanced encoding .* not implemented yet"):
         for page in reader.pages:
             page.extract_text()
+
+
+def test_get_font_width_from_default():  # L40
+    url = "https://corpora.tika.apache.org/base/docs/govdocs1/908/908104.pdf"
+    name = "tika-908104.pdf"
+    reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
+    for page in reader.pages:
+        page.extract_text()

tests/test_filters.py

@@ -1,9 +1,11 @@
 import string
+from io import BytesIO
 from itertools import product as cartesian_product
 
 import pytest
 
-from PyPDF2.errors import PdfReadError, PdfStreamError
+from PyPDF2 import PdfReader
+from PyPDF2.errors import PdfReadError, PdfReadWarning, PdfStreamError
 from PyPDF2.filters import (
     ASCII85Decode,
     ASCIIHexDecode,
@@ -13,6 +15,8 @@
 )
 from PyPDF2.generic import ArrayObject, DictionaryObject, NumberObject
 
+from . import get_pdf_from_url
+
 filter_inputs = (
     # "", '', """""",
     string.ascii_lowercase,
@@ -192,3 +196,23 @@ def test_CCITTFaxDecode():
         b"\x04\x00\x01\x00\x00\x00\x00\x00\x00\x00\x17\x01\x04\x00\x01\x00"
         b"\x00\x00\x00\x00\x00\x00\x00\x00"
     )
+
+
+def test_decompress_zlib_error():
+    url = "https://corpora.tika.apache.org/base/docs/govdocs1/952/952445.pdf"
+    name = "tika-952445.pdf"
+    with pytest.warns(PdfReadWarning, match=r"incorrect startxref pointer\(3\)"):
+        reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
+    for page in reader.pages:
+        page.extract_text()
+    # assert exc.value.args[0] == "Could not find xref table at specified location"
+
+
+def test_lzw_decode_neg1():
+    url = "https://corpora.tika.apache.org/base/docs/govdocs1/921/921632.pdf"
+    name = "tika-921632.pdf"
+    reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
+    with pytest.raises(PdfReadError) as exc:
+        for page in reader.pages:
+            page.extract_text()
+    assert exc.value.args[0] == "Missed the stop code in LZWDecode!"

tests/test_generic.py

@@ -451,3 +451,25 @@ def test_text_string_write_to_stream():
     reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
     for page in reader.pages:
         page.compress_content_streams()
+
+
+def test_name_object_read_from_stream_unicode_error():  # L588
+    url = "https://corpora.tika.apache.org/base/docs/govdocs1/974/974966.pdf"
+    name = "tika-974966.pdf"
+
+    reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
+    for page in reader.pages:
+        page.extract_text()
+
+
+def test_bool_repr():
+    url = "https://corpora.tika.apache.org/base/docs/govdocs1/932/932449.pdf"
+    name = "tika-932449.pdf"
+
+    reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
+    with open("tmp-fields-report.txt", "w") as fp:
+        fields = reader.get_fields(fileobj=fp)
+    assert fields
+
+    # cleanup
+    os.remove("tmp-fields-report.txt")

tests/test_page.py

@@ -258,3 +258,11 @@ def test_extract_text_page_pdf_impossible_decode_xform():
     ):
         for page in reader.pages:
             page.extract_text()
+
+
+def test_extract_text_operator_t_star():  # L1266, L1267
+    url = "https://corpora.tika.apache.org/base/docs/govdocs1/967/967943.pdf"
+    name = "tika-967943.pdf"
+    reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
+    for page in reader.pages:
+        page.extract_text()

tests/test_reader.py

@@ -334,7 +334,8 @@ def test_get_form(src, expected, expected_get_fields):
     fields = reader.get_form_text_fields()
     assert fields == expected
 
-    fields = reader.get_fields()
+    with open("tmp-fields-report.txt", "w") as f:
+        fields = reader.get_fields(fileobj=f)
     assert fields == expected_get_fields
     if fields:
         for field in fields.values():
@@ -352,6 +353,9 @@ def test_get_form(src, expected, expected_get_fields):
                 field.additional_actions,
             ]
 
+    # cleanup
+    os.remove("tmp-fields-report.txt")
+
 
 @pytest.mark.parametrize(
     ("src", "page_nb"),
@@ -751,6 +755,14 @@ def test_extract_text_pdf15():
         page.extract_text()
 
 
+def test_extract_text_xref_table_21_bytes_clrf():
+    # pdf/0264cf510015b2a4b395a15cb23c001e.pdf
+    url = "https://corpora.tika.apache.org/base/docs/govdocs1/956/956939.pdf"
+    reader = PdfReader(BytesIO(get_pdf_from_url(url, name="tika-956939.pdf")))
+    for page in reader.pages:
+        page.extract_text()
+
+
 def test_get_fields():
     url = "https://corpora.tika.apache.org/base/docs/govdocs1/972/972486.pdf"
     name = "tika-972486.pdf"
@@ -783,3 +795,22 @@ def test_get_fields_read_else_block3():
     with pytest.raises(PdfReadError) as exc:
         PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
     assert exc.value.args[0] == "Could not find xref table at specified location"
+
+
+def test_metadata_is_none():
+    url = "https://corpora.tika.apache.org/base/docs/govdocs1/963/963692.pdf"
+    name = "tika-963692.pdf"
+    reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
+    assert reader.metadata is None
+
+
+def test_get_fields_read_write_report():
+    url = "https://corpora.tika.apache.org/base/docs/govdocs1/909/909655.pdf"
+    name = "tika-909655.pdf"
+    reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
+    with open("tmp-fields-report.txt", "w") as fp:
+        fields = reader.get_fields(fileobj=fp)
+    assert fields
+
+    # cleanup
+    os.remove("tmp-fields-report.txt")