github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[formatter] add 'W' conversion - sanitize whitespace (#6582)

Browse Source 
https://github.com/mikf/gallery-dl/issues/6582#issuecomment-3090777073
This commit is contained in:
Mike Fährmann
2025-07-19 21:44:55 +02:00
parent 7bb4053396
commit 240f958707
3 changed files with 13 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/formatting.md
View File

@@ -128,6 +128,12 @@ Conversion specifiers allow to *convert* the value to a different form or type.
<td><code>{foo!n}</code></td> <td><code>{foo!n}</code></td>
<td><code>7</code></td> <td><code>7</code></td>
</tr> </tr>
<tr>
<td align="center"><code>W</code></td>
<td>Sanitize whitespace - Remove leading and trailing whitespace characters and replace <em>all</em> whitespace (sequences) with a single space <code> </code> character</td>
<td><code>{space!W}</code></td>
<td><code>Foo Bar</code></td>
</tr>
<tr> <tr>
<td align="center"><code>t</code></td> <td align="center"><code>t</code></td>
<td>Trim a string, i.e. remove leading and trailing whitespace characters</td> <td>Trim a string, i.e. remove leading and trailing whitespace characters</td>

1
gallery_dl/formatter.py
View File

@@ -541,6 +541,7 @@ _CONVERSIONS = {
"U": text.unescape, "U": text.unescape,
"H": lambda s: text.unescape(text.remove_html(s)), "H": lambda s: text.unescape(text.remove_html(s)),
"g": text.slugify, "g": text.slugify,
"W": text.sanitize_whitespace,
"S": util.to_string, "S": util.to_string,
"s": str, "s": str,
"r": repr, "r": repr,

8
test/test_formatter.py
View File

@@ -39,6 +39,7 @@ class TestFormatter(unittest.TestCase):
], ],
"n": None, "n": None,
"s": " \n\r\tSPACE ", "s": " \n\r\tSPACE ",
"S": " \n\r\tS P A\tC\nE ",
"h": "<p>foo </p> &amp; bar <p> </p>", "h": "<p>foo </p> &amp; bar <p> </p>",
"u": "&#x27;&lt; / &gt;&#x27;", "u": "&#x27;&lt; / &gt;&#x27;",
"t": 1262304000, "t": 1262304000,
@@ -61,6 +62,7 @@ class TestFormatter(unittest.TestCase):
self._run_test("{a!c}", "Hello world") self._run_test("{a!c}", "Hello world")
self._run_test("{a!C}", "Hello World") self._run_test("{a!C}", "Hello World")
self._run_test("{s!t}", "SPACE") self._run_test("{s!t}", "SPACE")
self._run_test("{S!t}", "S P A\tC\nE")
self._run_test("{a!U}", self.kwdict["a"]) self._run_test("{a!U}", self.kwdict["a"])
self._run_test("{u!U}", "'< / >'") self._run_test("{u!U}", "'< / >'")
self._run_test("{a!H}", self.kwdict["a"]) self._run_test("{a!H}", self.kwdict["a"])
@@ -90,6 +92,8 @@ class TestFormatter(unittest.TestCase):
self._run_test("{a!n}", 11) self._run_test("{a!n}", 11)
self._run_test("{l!n}", 3) self._run_test("{l!n}", 3)
self._run_test("{d!n}", 3) self._run_test("{d!n}", 3)
self._run_test("{s!W}", "SPACE")
self._run_test("{S!W}", "S P A C E")
self._run_test("{i_str!i}", 12345) self._run_test("{i_str!i}", 12345)
self._run_test("{i_str!f}", 12345.0) self._run_test("{i_str!f}", 12345.0)
self._run_test("{f_str!f}", 12.45) self._run_test("{f_str!f}", 12.45)
@@ -549,10 +553,10 @@ def noarg():
fmt4 = formatter.parse("\fM " + path + ":lengths") fmt4 = formatter.parse("\fM " + path + ":lengths")
self.assertEqual(fmt1.format_map(self.kwdict), "'Title' by Name") self.assertEqual(fmt1.format_map(self.kwdict), "'Title' by Name")
self.assertEqual(fmt2.format_map(self.kwdict), "142") self.assertEqual(fmt2.format_map(self.kwdict), "168")
self.assertEqual(fmt3.format_map(self.kwdict), "'Title' by Name") self.assertEqual(fmt3.format_map(self.kwdict), "'Title' by Name")
self.assertEqual(fmt4.format_map(self.kwdict), "142") self.assertEqual(fmt4.format_map(self.kwdict), "168")
with self.assertRaises(TypeError): with self.assertRaises(TypeError):
self.assertEqual(fmt0.format_map(self.kwdict), "") self.assertEqual(fmt0.format_map(self.kwdict), "")