From: "Laszlo Boszormenyi (GCS)" Date: Thu, 12 Jan 2023 18:54:41 -0500 Subject: disable network test for buildds don't have access Forwarded: no Last-Update: 2023-01-13 Just return from these tests. --- tests/test_cmap.py | 15 +++++++++++++++ tests/test_filters.py | 8 ++++++++ tests/test_generic.py | 8 ++++++++ tests/test_merger.py | 21 +++++++++++++++++++++ tests/test_page.py | 13 +++++++++++++ tests/test_reader.py | 28 ++++++++++++++++++++++++++++ tests/test_utils.py | 1 + tests/test_workflows.py | 21 +++++++++++++++++++++ tests/test_writer.py | 4 ++++ tests/test_xmp.py | 11 +++++++++++ 10 files changed, 130 insertions(+) diff --git a/tests/test_cmap.py b/tests/test_cmap.py index fc41b35..f97c7f7 100644 --- a/tests/test_cmap.py +++ b/tests/test_cmap.py @@ -14,6 +14,7 @@ def test_compute_space_width(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/923/923406.pdf" name = "tika-923406.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -25,6 +26,7 @@ def test_parse_to_unicode_process_rg(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/959/959173.pdf" name = "tika-959173.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -39,6 +41,7 @@ def test_parse_encoding_advanced_encoding_not_implemented(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/957/957144.pdf" name = "tika-957144.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) with pytest.warns(PdfReadWarning, match="Advanced encoding .* not implemented yet"): for page in reader.pages: @@ -49,6 +52,8 @@ def test_parse_encoding_advanced_encoding_not_implemented(): def test_get_font_width_from_default(): # L40 url = "https://corpora.tika.apache.org/base/docs/govdocs1/908/908104.pdf" name = "tika-908104.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -59,6 +64,8 @@ def test_multiline_bfrange(): # non regression test for iss_1285 url = "https://github.com/alexanderquispe/1REI05/raw/main/reports/report_1/The%20lean%20times%20in%20the%20Peruvian%20economy.pdf" name = "tika-908104.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -74,6 +81,8 @@ def test_bfchar_on_2_chars(): # iss #1293 url = "https://github.com/xyegithub/myBlog/raw/main/posts/c94b2364/paper_pdfs/ImageClassification/2007%2CASurveyofImageClassificationBasedTechniques.pdf" name = "ASurveyofImageClassificationBasedTechniques.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -84,6 +93,8 @@ def test_ascii_charset(): # iss #1312 url = "https://github.com/py-pdf/PyPDF2/files/9472500/main.pdf" name = "ascii charset.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) assert "/a" not in reader.pages[0].extract_text() @@ -92,6 +103,8 @@ def test_ascii_charset(): def test_iss1370(): url = "https://github.com/py-pdf/PyPDF2/files/9667138/cmap1370.pdf" name = "cmap1370.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) reader.pages[0].extract_text() @@ -100,5 +113,7 @@ def test_iss1370(): def test_iss1379(): url = "https://github.com/py-pdf/PyPDF2/files/9712729/02voc.pdf" name = "02voc.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) reader.pages[2].extract_text() diff --git a/tests/test_filters.py b/tests/test_filters.py index cc745c2..228c76d 100644 --- a/tests/test_filters.py +++ b/tests/test_filters.py @@ -205,6 +205,8 @@ def test_CCITTFaxDecode(): def test_decompress_zlib_error(mock_logger_warning): url = "https://corpora.tika.apache.org/base/docs/govdocs1/952/952445.pdf" name = "tika-952445.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -217,6 +219,8 @@ def test_decompress_zlib_error(mock_logger_warning): def test_lzw_decode_neg1(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/921/921632.pdf" name = "tika-921632.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) with pytest.raises(PdfReadError) as exc: for page in reader.pages: @@ -228,6 +232,8 @@ def test_lzw_decode_neg1(): def test_issue_399(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/976/976970.pdf" name = "tika-976970.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) reader.pages[1].extract_text() @@ -238,6 +244,8 @@ def test_image_without_imagemagic(): sys.modules["PIL"] = None url = "https://corpora.tika.apache.org/base/docs/govdocs1/914/914102.pdf" name = "tika-914102.pdf" + + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data, strict=True) diff --git a/tests/test_generic.py b/tests/test_generic.py index 886e4d3..a862840 100644 --- a/tests/test_generic.py +++ b/tests/test_generic.py @@ -605,6 +605,7 @@ def test_dict_read_from_stream(caplog): url = "https://corpora.tika.apache.org/base/docs/govdocs1/984/984877.pdf" name = "tika-984877.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -619,6 +620,7 @@ def test_parse_content_stream_peek_percentage(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/985/985770.pdf" name = "tika-985770.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -630,6 +632,7 @@ def test_read_inline_image_no_has_q(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/998/998719.pdf" name = "tika-998719.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -640,6 +643,7 @@ def test_read_inline_image_loc_neg_1(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/935/935066.pdf" name = "tika-935066.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -651,6 +655,7 @@ def test_text_string_write_to_stream(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/924/924562.pdf" name = "tika-924562.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.compress_content_streams() @@ -661,6 +666,7 @@ 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" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -671,6 +677,7 @@ def test_bool_repr(tmp_path): url = "https://corpora.tika.apache.org/base/docs/govdocs1/932/932449.pdf" name = "tika-932449.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) write_path = tmp_path / "tmp-fields-report.txt" with open(write_path, "w") as fp: @@ -692,6 +699,7 @@ def test_issue_997(mock_logger_warning): url = "https://github.com/py-pdf/PyPDF2/files/8908874/Exhibit_A-2_930_Enterprise_Zone_Tax_Credits_final.pdf" name = "gh-issue-997.pdf" + return merger = PdfMerger() merged_filename = "tmp-out.pdf" merger.append(BytesIO(get_pdf_from_url(url, name=name))) # here the error raises diff --git a/tests/test_merger.py b/tests/test_merger.py index 9cd1fb1..9c96b95 100644 --- a/tests/test_merger.py +++ b/tests/test_merger.py @@ -225,6 +225,8 @@ def test_merge_write_closed_fh(): def test_trim_outline_list(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/995/995175.pdf" name = "tika-995175.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) merger = PdfMerger() merger.append(reader) @@ -239,6 +241,8 @@ def test_trim_outline_list(): def test_zoom(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/994/994759.pdf" name = "tika-994759.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) merger = PdfMerger() merger.append(reader) @@ -253,6 +257,8 @@ def test_zoom(): def test_zoom_xyz_no_left(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/933/933322.pdf" name = "tika-933322.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) merger = PdfMerger() merger.append(reader) @@ -267,6 +273,8 @@ def test_zoom_xyz_no_left(): def test_outline_item(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/997/997511.pdf" name = "tika-997511.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) merger = PdfMerger() merger.append(reader) @@ -282,6 +290,8 @@ def test_outline_item(): def test_trim_outline(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/982/982336.pdf" name = "tika-982336.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) merger = PdfMerger() merger.append(reader) @@ -297,6 +307,8 @@ def test_trim_outline(): def test1(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/923/923621.pdf" name = "tika-923621.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) merger = PdfMerger() merger.append(reader) @@ -313,6 +325,8 @@ def test_sweep_recursion1(): # TODO: This test looks like an infinite loop. url = "https://corpora.tika.apache.org/base/docs/govdocs1/924/924546.pdf" name = "tika-924546.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) merger = PdfMerger() merger.append(reader) @@ -343,6 +357,7 @@ def test_sweep_recursion1(): ], ) def test_sweep_recursion2(url, name): + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) merger = PdfMerger() merger.append(reader) @@ -360,6 +375,8 @@ def test_sweep_recursion2(url, name): def test_sweep_indirect_list_newobj_is_None(caplog): url = "https://corpora.tika.apache.org/base/docs/govdocs1/906/906769.pdf" name = "tika-906769.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) merger = PdfMerger() merger.append(reader) @@ -379,6 +396,8 @@ def test_iss1145(): # issue with FitH destination with null param url = "https://github.com/py-pdf/PyPDF2/files/9164743/file-0.pdf" name = "iss1145.pdf" + + return merger = PdfMerger() merger.append(PdfReader(BytesIO(get_pdf_from_url(url, name=name)))) merger.close() @@ -407,6 +426,8 @@ def test_deprecate_bookmark_decorator_output(): def test_iss1344(caplog): url = "https://github.com/py-pdf/PyPDF2/files/9549001/input.pdf" name = "iss1344.pdf" + + return m = PdfMerger() m.append(PdfReader(BytesIO(get_pdf_from_url(url, name=name)))) b = BytesIO() diff --git a/tests/test_page.py b/tests/test_page.py index 2c2ea3a..f35051e 100644 --- a/tests/test_page.py +++ b/tests/test_page.py @@ -83,6 +83,7 @@ def test_page_operations(pdf_path, password): This should be done way more thoroughly: It should be checked if the output is as expected. """ + return if pdf_path.startswith("http"): pdf_path = BytesIO(get_pdf_from_url(pdf_path, pdf_path.split("/")[-1])) else: @@ -286,6 +287,8 @@ def test_multi_language(): @pytest.mark.external def test_extract_text_single_quote_op(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/964/964029.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name="tika-964029.pdf"))) for page in reader.pages: page.extract_text() @@ -294,6 +297,7 @@ def test_extract_text_single_quote_op(): @pytest.mark.external def test_no_ressources_on_text_extract(): url = "https://github.com/py-pdf/PyPDF2/files/9428434/TelemetryTX_EM.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name="tika-964029.pdf"))) for page in reader.pages: page.extract_text() @@ -304,6 +308,8 @@ def test_iss_1142(): # check fix for problem of context save/restore (q/Q) url = "https://github.com/py-pdf/PyPDF2/files/9150656/ST.2019.PDF" name = "st2019.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) txt = reader.pages[3].extract_text() # The following text is contained in two different cells: @@ -344,6 +350,7 @@ def test_iss_1142(): ], ) def test_extract_text_page_pdf(url, name): + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -354,6 +361,8 @@ def test_extract_text_page_pdf(url, name): def test_extract_text_page_pdf_impossible_decode_xform(caplog): url = "https://corpora.tika.apache.org/base/docs/govdocs1/972/972962.pdf" name = "tika-972962.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -366,6 +375,8 @@ def test_extract_text_page_pdf_impossible_decode_xform(caplog): 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" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() @@ -820,6 +831,7 @@ def test_text_extraction_issue_1091(): def test_empyt_password_1088(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/941/941536.pdf" name = "tika-941536.pdf" + return stream = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(stream) len(reader.pages) @@ -865,6 +877,7 @@ def test_read_link_annotation(): def test_no_resources(): url = "https://github.com/py-pdf/PyPDF2/files/9572045/108.pdf" name = "108.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) page_one = reader.pages[0] page_two = reader.pages[0] diff --git a/tests/test_reader.py b/tests/test_reader.py index 25018ae..7945e32 100644 --- a/tests/test_reader.py +++ b/tests/test_reader.py @@ -752,6 +752,7 @@ def test_convertToInt_deprecated(): @pytest.mark.external def test_iss925(): url = "https://github.com/py-pdf/PyPDF2/files/8796328/1.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name="iss925.pdf"))) for page_sliced in reader.pages: @@ -808,6 +809,7 @@ def test_read_form_416(): url = ( "https://www.fda.gov/downloads/AboutFDA/ReportsManualsForms/Forms/UCM074728.pdf" ) + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name="issue_416.pdf"))) fields = reader.get_form_text_fields() assert len(fields) > 0 @@ -818,6 +820,7 @@ def test_extract_text_xref_issue_2(caplog): # pdf/0264cf510015b2a4b395a15cb23c001e.pdf url = "https://corpora.tika.apache.org/base/docs/govdocs1/981/981961.pdf" msg = "incorrect startxref pointer(2)" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name="tika-981961.pdf"))) for page in reader.pages: page.extract_text() @@ -830,6 +833,7 @@ def test_extract_text_xref_issue_3(caplog): # pdf/0264cf510015b2a4b395a15cb23c001e.pdf url = "https://corpora.tika.apache.org/base/docs/govdocs1/977/977774.pdf" msg = "incorrect startxref pointer(3)" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name="tika-977774.pdf"))) for page in reader.pages: page.extract_text() @@ -840,6 +844,7 @@ def test_extract_text_xref_issue_3(caplog): def test_extract_text_pdf15(): # pdf/0264cf510015b2a4b395a15cb23c001e.pdf url = "https://corpora.tika.apache.org/base/docs/govdocs1/976/976030.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name="tika-976030.pdf"))) for page in reader.pages: page.extract_text() @@ -849,6 +854,7 @@ def test_extract_text_pdf15(): def test_extract_text_xref_table_21_bytes_clrf(): # pdf/0264cf510015b2a4b395a15cb23c001e.pdf url = "https://corpora.tika.apache.org/base/docs/govdocs1/956/956939.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name="tika-956939.pdf"))) for page in reader.pages: page.extract_text() @@ -858,6 +864,7 @@ def test_extract_text_xref_table_21_bytes_clrf(): def test_get_fields(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/972/972486.pdf" name = "tika-972486.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) fields = reader.get_fields() assert fields is not None @@ -871,6 +878,8 @@ def test_get_fields_read_else_block(): # covers also issue 1089 url = "https://corpora.tika.apache.org/base/docs/govdocs1/934/934771.pdf" name = "tika-934771.pdf" + + return PdfReader(BytesIO(get_pdf_from_url(url, name=name))) @@ -878,6 +887,8 @@ def test_get_fields_read_else_block(): def test_get_fields_read_else_block2(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/914/914902.pdf" name = "tika-914902.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) fields = reader.get_fields() assert fields is None @@ -888,6 +899,8 @@ def test_get_fields_read_else_block2(): def test_get_fields_read_else_block3(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/957/957721.pdf" name = "tika-957721.pdf" + + return PdfReader(BytesIO(get_pdf_from_url(url, name=name))) @@ -895,6 +908,8 @@ def test_get_fields_read_else_block3(): def test_metadata_is_none(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/963/963692.pdf" name = "tika-963692.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) assert reader.metadata is None @@ -903,6 +918,7 @@ def test_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" + return 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) @@ -928,6 +944,7 @@ def test_xfa(src): def test_xfa_non_empty(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/942/942050.pdf" name = "tika-942050.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) assert list(reader.xfa.keys()) == [ "preamble", @@ -956,6 +973,7 @@ def test_header(src, pdf_header): def test_outline_color(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/924/924546.pdf" name = "tika-924546.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) assert reader.outline[0].color == [0, 0, 1] @@ -964,6 +982,7 @@ def test_outline_color(): def test_outline_font_format(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/924/924546.pdf" name = "tika-924546.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) assert reader.outline[0].font_format == 2 @@ -1092,6 +1111,7 @@ def test_named_destination(): # 1st case : the named_dest are stored directly as a dictionnary, PDF1.1 style url = "https://github.com/py-pdf/PyPDF2/files/9197028/lorem_ipsum.pdf" name = "lorem_ipsum.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) assert len(reader.named_destinations) > 0 # 2nd case : Dest below names and with Kids... @@ -1107,6 +1127,7 @@ def test_named_destination(): def test_outline_with_missing_named_destination(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/913/913678.pdf" name = "tika-913678.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) # outline items in document reference a named destination that is not defined assert reader.outline[1][0].title.startswith("Report for 2002AZ3B: Microbial") @@ -1116,6 +1137,7 @@ def test_outline_with_missing_named_destination(): def test_outline_with_empty_action(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/924/924546.pdf" name = "tika-924546.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) # outline items (entitled Tables and Figures) utilize an empty action (/A) # that has no type or destination @@ -1133,6 +1155,7 @@ def test_PdfReaderMultipleDefinitions(caplog): # iss325 url = "https://github.com/py-pdf/PyPDF2/files/9176644/multipledefs.pdf" name = "multipledefs.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) reader.pages[0].extract_text() assert normalize_warnings(caplog.text) == [ @@ -1159,6 +1182,7 @@ def test_corrupted_xref_table(): # issue #1292 url = "https://github.com/py-pdf/PyPDF2/files/9444747/BreezeManual.orig.pdf" name = "BreezeMan1.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) reader.pages[0].extract_text() url = "https://github.com/py-pdf/PyPDF2/files/9444748/BreezeManual.failed.pdf" @@ -1172,6 +1196,7 @@ def test_reader(caplog): # iss #1273 url = "https://github.com/py-pdf/PyPDF2/files/9464742/shiv_resume.pdf" name = "shiv_resume.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) assert "Previous trailer can not be read" in caplog.text caplog.clear() @@ -1190,6 +1215,7 @@ def test_zeroing_xref(): # iss #328 url = "https://github.com/py-pdf/PyPDF2/files/9066120/UTA_OSHA_3115_Fall_Protection_Training_09162021_.pdf" name = "UTA_OSHA.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) len(reader.pages) @@ -1197,6 +1223,7 @@ def test_zeroing_xref(): def test_thread(): url = "https://github.com/py-pdf/PyPDF2/files/9066120/UTA_OSHA_3115_Fall_Protection_Training_09162021_.pdf" name = "UTA_OSHA.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) assert reader.threads is None url = "https://corpora.tika.apache.org/base/docs/govdocs1/924/924666.pdf" @@ -1209,6 +1236,7 @@ def test_thread(): def test_build_outline_item(caplog): url = "https://github.com/py-pdf/PyPDF2/files/9464742/shiv_resume.pdf" name = "shiv_resume.pdf" + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) outline = reader._build_outline_item( DictionaryObject( diff --git a/tests/test_utils.py b/tests/test_utils.py index a5f5fa1..dcccd87 100644 --- a/tests/test_utils.py +++ b/tests/test_utils.py @@ -256,6 +256,7 @@ def test_escapedcode_followed_by_int(): url = "https://github.com/timedegree/playground_files/raw/main/%E8%AE%BA%E6%96%87/AN%20EXACT%20ANALYTICAL%20SOLUTION%20OF%20KEPLER'S%20EQUATION.pdf" name = "keppler.pdf" + return reader = PdfReader(io.BytesIO(get_pdf_from_url(url, name=name))) for page in reader.pages: page.extract_text() diff --git a/tests/test_workflows.py b/tests/test_workflows.py index 7720a66..36098a9 100644 --- a/tests/test_workflows.py +++ b/tests/test_workflows.py @@ -243,6 +243,7 @@ def test_rotate_45(): ], ) def test_extract_textbench(enable, url, pages, print_result=False): + return if not enable: return try: @@ -314,6 +315,7 @@ def test_orientations(): ], ) def test_overlay(base_path, overlay_path): + return if base_path.startswith("http"): base_path = BytesIO(get_pdf_from_url(base_path, name="tika-935981.pdf")) else: @@ -346,6 +348,7 @@ def test_overlay(base_path, overlay_path): ], ) def test_merge_with_warning(tmp_path, url, name): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data) merger = PdfMerger() @@ -365,6 +368,7 @@ def test_merge_with_warning(tmp_path, url, name): ], ) def test_merge(tmp_path, url, name): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data) merger = PdfMerger() @@ -383,6 +387,7 @@ def test_merge(tmp_path, url, name): ], ) def test_get_metadata(url, name): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data) reader.metadata @@ -461,6 +466,7 @@ def test_get_metadata(url, name): ], ) def test_extract_text(url, name, strict, exception): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data, strict=strict) if not exception: @@ -489,6 +495,7 @@ def test_extract_text(url, name, strict, exception): ], ) def test_compress_raised(url, name): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data) # no more error since iss #1090 fix @@ -519,6 +526,7 @@ def test_compress_raised(url, name): ], ) def test_compress(url, name, strict): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data, strict=strict) # TODO: which page exactly? @@ -538,6 +546,7 @@ def test_compress(url, name, strict): ], ) def test_get_fields_warns(tmp_path, caplog, url, name): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data) write_path = tmp_path / "tmp.txt" @@ -559,6 +568,7 @@ def test_get_fields_warns(tmp_path, caplog, url, name): ], ) def test_get_fields_no_warning(tmp_path, url, name): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data) write_path = tmp_path / "tmp.txt" @@ -572,6 +582,8 @@ def test_get_fields_no_warning(tmp_path, url, name): def test_scale_rectangle_indirect_object(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/999/999944.pdf" name = "tika-999944.pdf" + + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data) @@ -657,6 +669,7 @@ def test_merge_output(caplog): ], ) def test_image_extraction(url, name): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data) @@ -685,6 +698,7 @@ def test_image_extraction_strict(): # Emits log messages url = "https://corpora.tika.apache.org/base/docs/govdocs1/914/914102.pdf" name = "tika-914102.pdf" + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data, strict=True) @@ -719,6 +733,7 @@ def test_image_extraction_strict(): ], ) def test_image_extraction2(url, name): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data) @@ -757,6 +772,7 @@ def test_image_extraction2(url, name): ], ) def test_get_outline(url, name): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data) reader.outline @@ -777,6 +793,7 @@ def test_get_outline(url, name): ], ) def test_get_xfa(url, name): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data) reader.xfa @@ -809,6 +826,7 @@ def test_get_xfa(url, name): ], ) def test_get_fonts(url, name, strict): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data, strict=strict) for page in reader.pages: @@ -842,6 +860,7 @@ def test_get_fonts(url, name, strict): ], ) def test_get_xmp(url, name, strict): + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data, strict=strict) xmp_info = reader.xmp_metadata @@ -877,6 +896,8 @@ def test_get_xmp(url, name, strict): def test_tounicode_is_identity(): url = "https://github.com/py-pdf/PyPDF2/files/9998335/FP_Thesis.pdf" name = "FP_Thesis.pdf" + + return data = BytesIO(get_pdf_from_url(url, name=name)) reader = PdfReader(data, strict=False) reader.pages[0].extract_text() diff --git a/tests/test_writer.py b/tests/test_writer.py index 0e63b0a..b9df105 100644 --- a/tests/test_writer.py +++ b/tests/test_writer.py @@ -655,6 +655,8 @@ def test_sweep_indirect_references_nullobject_exception(): # TODO: Check this more closely... this looks weird url = "https://corpora.tika.apache.org/base/docs/govdocs1/924/924666.pdf" name = "tika-924666.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) merger = PdfMerger() merger.append(reader) @@ -669,6 +671,8 @@ def test_sweep_indirect_references_nullobject_exception(): def test_write_outline_item_on_page_fitv(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/922/922840.pdf" name = "tika-922840.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) merger = PdfMerger() merger.append(reader) diff --git a/tests/test_xmp.py b/tests/test_xmp.py index 5b8202c..1a46fed 100644 --- a/tests/test_xmp.py +++ b/tests/test_xmp.py @@ -99,6 +99,7 @@ def test_identity(x): ], ) def test_xmpmm(url, name, xmpmm_instance_id): + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) xmp_metadata = reader.xmp_metadata assert xmp_metadata.xmpmm_instance_id == xmpmm_instance_id @@ -110,6 +111,8 @@ def test_xmpmm(url, name, xmpmm_instance_id): def test_dc_description(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/953/953770.pdf" name = "tika-953770.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) xmp_metadata = reader.xmp_metadata assert xmp_metadata.dc_description == { @@ -125,6 +128,8 @@ def test_dc_description(): def test_dc_creator(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/953/953770.pdf" name = "tika-953770.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) xmp_metadata = reader.xmp_metadata assert xmp_metadata.dc_creator == ["U.S. Fish and Wildlife Service"] @@ -136,6 +141,8 @@ def test_dc_creator(): def test_custom_properties(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/986/986065.pdf" name = "tika-986065.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) xmp_metadata = reader.xmp_metadata assert xmp_metadata.custom_properties == {"Style": "Searchable Image (Exact)"} @@ -147,6 +154,8 @@ def test_custom_properties(): def test_dc_subject(): url = "https://corpora.tika.apache.org/base/docs/govdocs1/959/959519.pdf" name = "tika-959519.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) xmp_metadata = reader.xmp_metadata assert xmp_metadata.dc_subject == [ @@ -178,6 +187,8 @@ def test_dc_subject(): def test_issue585(): url = "https://github.com/mstamy2/PyPDF2/files/5536984/test.pdf" name = "mstamy2-5536984.pdf" + + return reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name))) with pytest.raises(PdfReadError) as exc: reader.xmp_metadata