Mercurial > hgrepos > Python2 > PyMuPDF
annotate tests/test_tesseract.py @ 39:a6bc019ac0b2 upstream
ADD: PyMuPDF v1.26.5: the original sdist.
| author | Franz Glasner <fzglas.hg@dom66.de> |
|---|---|
| date | Sat, 11 Oct 2025 11:19:58 +0200 |
| parents | 1d09e1dec1d9 |
| children |
| rev | line source |
|---|---|
|
1
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
1 import os |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
2 import platform |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
3 import textwrap |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
4 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
5 import pymupdf |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
6 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
7 def test_tesseract(): |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
8 ''' |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
9 This checks that MuPDF has been built with tesseract support. |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
10 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
11 By default we don't supply a valid `tessdata` directory, and just assert |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
12 that attempting to use Tesseract raises the expected error (which checks |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
13 that MuPDF is built with Tesseract support). |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
14 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
15 But if TESSDATA_PREFIX is set in the environment, we assert that |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
16 FzPage.get_textpage_ocr() succeeds. |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
17 ''' |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
18 path = os.path.abspath( f'{__file__}/../resources/2.pdf') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
19 doc = pymupdf.open( path) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
20 page = doc[5] |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
21 if hasattr(pymupdf, 'mupdf'): |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
22 # rebased. |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
23 if pymupdf.mupdf_version_tuple < (1, 25, 4): |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
24 tail = 'OCR initialisation failed' |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
25 else: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
26 tail = 'Tesseract language initialisation failed' |
|
39
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
27 if os.environ.get('PYODIDE_ROOT'): |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
28 e_expected = 'code=6: No OCR support in this build' |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
29 e_expected_type = pymupdf.mupdf.FzErrorUnsupported |
|
1
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
30 else: |
|
39
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
31 e_expected = f'code=3: {tail}' |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
32 if platform.system() == 'OpenBSD': |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
33 # 2023-12-12: For some reason the SWIG catch code only catches |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
34 # the exception as FzErrorBase. |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
35 e_expected_type = pymupdf.mupdf.FzErrorBase |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
36 print(f'OpenBSD workaround - expecting FzErrorBase, not FzErrorLibrary.') |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
37 else: |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
38 e_expected_type = pymupdf.mupdf.FzErrorLibrary |
|
1
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
39 else: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
40 # classic. |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
41 e_expected = 'OCR initialisation failed' |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
42 e_expected_type = None |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
43 tessdata_prefix = os.environ.get('TESSDATA_PREFIX') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
44 if tessdata_prefix: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
45 tp = page.get_textpage_ocr(full=True) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
46 print(f'test_tesseract(): page.get_textpage_ocr() succeeded') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
47 else: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
48 try: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
49 tp = page.get_textpage_ocr(full=True, tessdata='/foo/bar') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
50 except Exception as e: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
51 e_text = str(e) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
52 print(f'Received exception as expected.') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
53 print(f'{type(e)=}') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
54 print(f'{e_text=}') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
55 assert e_text == e_expected, f'Unexpected exception: {e_text!r}' |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
56 if e_expected_type: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
57 print(f'{e_expected_type=}') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
58 assert type(e) == e_expected_type, f'{type(e)=} != {e_expected_type=}.' |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
59 else: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
60 assert 0, f'Expected exception {e_expected!r}' |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
61 rebased = hasattr(pymupdf, 'mupdf') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
62 if rebased: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
63 wt = pymupdf.TOOLS.mupdf_warnings() |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
64 if pymupdf.mupdf_version_tuple < (1, 25, 4): |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
65 assert wt == ( |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
66 'UNHANDLED EXCEPTION!\n' |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
67 'library error: Tesseract initialisation failed' |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
68 ) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
69 else: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
70 assert not wt |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
71 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
72 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
73 def test_3842b(): |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
74 # Check Tesseract failure when given a bogus languages. |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
75 # |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
76 # Note that Tesseract seems to output its own diagnostics. |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
77 # |
|
39
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
78 if os.environ.get('PYODIDE_ROOT'): |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
79 print('test_3842b(): not running on Pyodide - cannot run child processes.') |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
80 return |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
81 |
|
1
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
82 path = os.path.normpath(f'{__file__}/../../tests/resources/test_3842.pdf') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
83 with pymupdf.open(path) as document: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
84 page = document[6] |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
85 try: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
86 partial_tp = page.get_textpage_ocr(flags=0, full=False, language='qwerty') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
87 except Exception as e: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
88 print(f'test_3842b(): received exception: {e}') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
89 if 'No tessdata specified and Tesseract is not installed' in str(e): |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
90 pass |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
91 else: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
92 if pymupdf.mupdf_version_tuple < (1, 25, 4): |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
93 assert 'OCR initialisation failed' in str(e) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
94 wt = pymupdf.TOOLS.mupdf_warnings() |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
95 assert wt == 'UNHANDLED EXCEPTION!\nlibrary error: Tesseract initialisation failed\nUNHANDLED EXCEPTION!\nlibrary error: Tesseract initialisation failed', \ |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
96 f'Unexpected {wt=}' |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
97 else: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
98 assert 'Tesseract language initialisation failed' in str(e) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
99 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
100 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
101 def test_3842(): |
|
39
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
102 if os.environ.get('PYODIDE_ROOT'): |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
103 print('test_3842(): not running on Pyodide - cannot run child processes.') |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
104 return |
|
a6bc019ac0b2
ADD: PyMuPDF v1.26.5: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
1
diff
changeset
|
105 |
|
1
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
106 path = os.path.normpath(f'{__file__}/../../tests/resources/test_3842.pdf') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
107 with pymupdf.open(path) as document: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
108 page = document[6] |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
109 try: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
110 partial_tp = page.get_textpage_ocr(flags=0, full=False) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
111 except Exception as e: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
112 print(f'test_3842(): received exception: {e}', flush=1) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
113 if 'No tessdata specified and Tesseract is not installed' in str(e): |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
114 pass |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
115 elif 'Tesseract language initialisation failed' in str(e): |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
116 pass |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
117 else: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
118 assert 0, f'Unexpected exception text: {str(e)=}' |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
119 else: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
120 text = page.get_text(textpage=partial_tp) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
121 print() |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
122 print(text) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
123 print(f'text:\n{text!r}') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
124 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
125 # 2024-11-29: This is the current incorrect output. We use |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
126 # underscores for lines containing entirely whitespace (which |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
127 # textwrap.dedent() unfortunately replaces with empty lines). |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
128 text_expected = textwrap.dedent(''' |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
129 NIST SP 800-223 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
130 _ |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
131 High-Performance Computing Security |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
132 February 2024 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
133 _ |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
134 __ |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
135 iii |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
136 Table of Contents |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
137 1. Introduction ...................................................................................................................................1 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
138 2. HPC System Reference Architecture and Main Components ............................................................2 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
139 2.1.1. Components of the High-Performance Computing Zone ............................................................. 3 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
140 2.1.2. Components of the Data Storage Zone ........................................................................................ 4 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
141 2.1.3. Parallel File System ....................................................................................................................... 4 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
142 2.1.4. Archival and Campaign Storage .................................................................................................... 5 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
143 2.1.5. Burst Buffer .................................................................................................................................. 5 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
144 2.1.6. Components of the Access Zone .................................................................................................. 6 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
145 2.1.7. Components of the Management Zone ....................................................................................... 6 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
146 2.1.8. General Architecture and Characteristics .................................................................................... 6 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
147 2.1.9. Basic Services ................................................................................................................................ 7 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
148 2.1.10. Configuration Management ....................................................................................................... 7 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
149 2.1.11. HPC Scheduler and Workflow Management .............................................................................. 7 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
150 2.1.12. HPC Software .............................................................................................................................. 8 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
151 2.1.13. User Software ............................................................................................................................. 8 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
152 2.1.14. Site-Provided Software and Vendor Software ........................................................................... 8 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
153 2.1.15. Containerized Software in HPC .................................................................................................. 9 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
154 3. HPC Threat Analysis...................................................................................................................... 10 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
155 3.2.1. Access Zone Threats ................................................................................................................... 11 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
156 3.2.2. Management Zone Threats ........................................................................................................ 11 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
157 3.2.3. High-Performance Computing Zone Threats .............................................................................. 12 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
158 3.2.4. Data Storage Zone Threats ......................................................................................................... 12 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
159 4. HPC Security Posture, Challenges, and Recommendations ............................................................. 14 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
160 5. Conclusions .................................................................................................................................. 19 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
161 ''', |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
162 )[1:].replace('_', ' ') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
163 print(f'text_expected:\n{text_expected!r}') |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
164 assert text == text_expected |
