Mercurial > hgrepos > Python2 > PyMuPDF
annotate tests/test_textsearch.py @ 46:7ee69f120f19 default tip
>>>>> tag v1.26.5+1 for changeset b74429b0f5c4
| author | Franz Glasner <fzglas.hg@dom66.de> |
|---|---|
| date | Sat, 11 Oct 2025 17:17:30 +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 """ |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
2 "test_search1": |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
3 Search for some text on a PDF page, and compare content of returned hit |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
4 rectangle with the searched text. |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
5 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
6 "test_search2": |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
7 Text search with 'clip' parameter - clip rectangle contains two occurrences |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
8 of searched text. Confirm search locations are inside clip. |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
9 """ |
|
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 import os |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
12 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
13 import pymupdf |
|
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 scriptdir = os.path.abspath(os.path.dirname(__file__)) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
16 filename1 = os.path.join(scriptdir, "resources", "2.pdf") |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
17 filename2 = os.path.join(scriptdir, "resources", "github_sample.pdf") |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
18 filename3 = os.path.join(scriptdir, "resources", "text-find-ligatures.pdf") |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
19 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
20 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
21 def test_search1(): |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
22 doc = pymupdf.open(filename1) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
23 page = doc[0] |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
24 needle = "mupdf" |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
25 rlist = page.search_for(needle) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
26 assert rlist != [] |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
27 for rect in rlist: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
28 assert needle in page.get_textbox(rect).lower() |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
29 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
30 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
31 def test_search2(): |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
32 doc = pymupdf.open(filename2) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
33 page = doc[0] |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
34 needle = "the" |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
35 clip = pymupdf.Rect(40.5, 228.31436157226562, 346.5226135253906, 239.5338592529297) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
36 rl = page.search_for(needle, clip=clip) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
37 assert len(rl) == 2 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
38 for r in rl: |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
39 assert r in clip |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
40 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
41 |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
42 def test_search3(): |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
43 """Ensure we find text whether or not it contains ligatures.""" |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
44 doc = pymupdf.open(filename3) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
45 page = doc[0] |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
46 needle = "flag" |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
47 hits = page.search_for(needle, flags=pymupdf.TEXTFLAGS_SEARCH) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
48 assert len(hits) == 2 # all occurrences found |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
49 hits = page.search_for( |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
50 needle, flags=pymupdf.TEXTFLAGS_SEARCH | pymupdf.TEXT_PRESERVE_LIGATURES |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
51 ) |
|
1d09e1dec1d9
ADD: PyMuPDF v1.26.4: the original sdist.
Franz Glasner <fzglas.hg@dom66.de>
parents:
diff
changeset
|
52 assert len(hits) == 1 # only found text without ligatures |
