re2 2.0.0.beta2 → 2.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/LICENSE-DEPENDENCIES.txt +237 -0
- data/LICENSE.txt +1 -1
- data/README.md +51 -18
- data/ext/re2/re2.cc +74 -23
- data/lib/re2/version.rb +1 -1
- data/re2.gemspec +5 -4
- data/spec/kernel_spec.rb +3 -3
- data/spec/re2/match_data_spec.rb +24 -0
- data/spec/re2/regexp_spec.rb +6 -0
- data/spec/re2/scanner_spec.rb +76 -22
- data/spec/re2/set_spec.rb +41 -1
- data/spec/re2/string_spec.rb +7 -3
- data/spec/re2_spec.rb +104 -10
- data/spec/spec_helper.rb +10 -0
- metadata +8 -6
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 37e251e652dcc758e2d18f0734cf6fe9af62fa23b3ed127175c27cc439e80451
|
|
4
|
+
data.tar.gz: 536b7cf0e815c480638a381dfca47677149d0c8d2f711105db34439e0c2d9e09
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 711ba1845bbc96f4a2120ec595f77316d08803bcddb995758871232811b23fa5a2c7cda1949d5fee2f86279ecba694001c530efe7bc29767aa7b5371fe4b5613
|
|
7
|
+
data.tar.gz: f13f0c6d838775667d3d0ed507397e6dadad55c352e8968d7af8295c5dd7e87f6f987c813042c7edee453ded849c9dbd9cc26d440966efe48eda698d29db616b
|
|
@@ -0,0 +1,237 @@
|
|
|
1
|
+
# Vendored Dependency Licenses
|
|
2
|
+
|
|
3
|
+
The library re2 (which lives at https://github.com/mudge/re2) may include the source code for RE2 (which lives at https://github.com/google/re2) and Abseil (which lives at https://abseil.io).
|
|
4
|
+
|
|
5
|
+
The license terms shipped with RE2 are included here for your convenience:
|
|
6
|
+
|
|
7
|
+
// Copyright (c) 2009 The RE2 Authors. All rights reserved.
|
|
8
|
+
//
|
|
9
|
+
// Redistribution and use in source and binary forms, with or without
|
|
10
|
+
// modification, are permitted provided that the following conditions are
|
|
11
|
+
// met:
|
|
12
|
+
//
|
|
13
|
+
// * Redistributions of source code must retain the above copyright
|
|
14
|
+
// notice, this list of conditions and the following disclaimer.
|
|
15
|
+
// * Redistributions in binary form must reproduce the above
|
|
16
|
+
// copyright notice, this list of conditions and the following disclaimer
|
|
17
|
+
// in the documentation and/or other materials provided with the
|
|
18
|
+
// distribution.
|
|
19
|
+
// * Neither the name of Google Inc. nor the names of its
|
|
20
|
+
// contributors may be used to endorse or promote products derived from
|
|
21
|
+
// this software without specific prior written permission.
|
|
22
|
+
//
|
|
23
|
+
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
24
|
+
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
25
|
+
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
26
|
+
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
|
27
|
+
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
28
|
+
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
29
|
+
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
30
|
+
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
31
|
+
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
32
|
+
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
33
|
+
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
34
|
+
|
|
35
|
+
The license terms shipped with Abseil are included here for your convenience:
|
|
36
|
+
|
|
37
|
+
Apache License
|
|
38
|
+
Version 2.0, January 2004
|
|
39
|
+
https://www.apache.org/licenses/
|
|
40
|
+
|
|
41
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
42
|
+
|
|
43
|
+
1. Definitions.
|
|
44
|
+
|
|
45
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
46
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
47
|
+
|
|
48
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
49
|
+
the copyright owner that is granting the License.
|
|
50
|
+
|
|
51
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
52
|
+
other entities that control, are controlled by, or are under common
|
|
53
|
+
control with that entity. For the purposes of this definition,
|
|
54
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
55
|
+
direction or management of such entity, whether by contract or
|
|
56
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
57
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
58
|
+
|
|
59
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
60
|
+
exercising permissions granted by this License.
|
|
61
|
+
|
|
62
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
63
|
+
including but not limited to software source code, documentation
|
|
64
|
+
source, and configuration files.
|
|
65
|
+
|
|
66
|
+
"Object" form shall mean any form resulting from mechanical
|
|
67
|
+
transformation or translation of a Source form, including but
|
|
68
|
+
not limited to compiled object code, generated documentation,
|
|
69
|
+
and conversions to other media types.
|
|
70
|
+
|
|
71
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
72
|
+
Object form, made available under the License, as indicated by a
|
|
73
|
+
copyright notice that is included in or attached to the work
|
|
74
|
+
(an example is provided in the Appendix below).
|
|
75
|
+
|
|
76
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
77
|
+
form, that is based on (or derived from) the Work and for which the
|
|
78
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
79
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
80
|
+
of this License, Derivative Works shall not include works that remain
|
|
81
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
82
|
+
the Work and Derivative Works thereof.
|
|
83
|
+
|
|
84
|
+
"Contribution" shall mean any work of authorship, including
|
|
85
|
+
the original version of the Work and any modifications or additions
|
|
86
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
87
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
88
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
89
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
90
|
+
means any form of electronic, verbal, or written communication sent
|
|
91
|
+
to the Licensor or its representatives, including but not limited to
|
|
92
|
+
communication on electronic mailing lists, source code control systems,
|
|
93
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
94
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
95
|
+
excluding communication that is conspicuously marked or otherwise
|
|
96
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
97
|
+
|
|
98
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
99
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
100
|
+
subsequently incorporated within the Work.
|
|
101
|
+
|
|
102
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
103
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
104
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
105
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
106
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
107
|
+
Work and such Derivative Works in Source or Object form.
|
|
108
|
+
|
|
109
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
110
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
111
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
112
|
+
(except as stated in this section) patent license to make, have made,
|
|
113
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
114
|
+
where such license applies only to those patent claims licensable
|
|
115
|
+
by such Contributor that are necessarily infringed by their
|
|
116
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
117
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
118
|
+
institute patent litigation against any entity (including a
|
|
119
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
120
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
121
|
+
or contributory patent infringement, then any patent licenses
|
|
122
|
+
granted to You under this License for that Work shall terminate
|
|
123
|
+
as of the date such litigation is filed.
|
|
124
|
+
|
|
125
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
126
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
127
|
+
modifications, and in Source or Object form, provided that You
|
|
128
|
+
meet the following conditions:
|
|
129
|
+
|
|
130
|
+
(a) You must give any other recipients of the Work or
|
|
131
|
+
Derivative Works a copy of this License; and
|
|
132
|
+
|
|
133
|
+
(b) You must cause any modified files to carry prominent notices
|
|
134
|
+
stating that You changed the files; and
|
|
135
|
+
|
|
136
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
137
|
+
that You distribute, all copyright, patent, trademark, and
|
|
138
|
+
attribution notices from the Source form of the Work,
|
|
139
|
+
excluding those notices that do not pertain to any part of
|
|
140
|
+
the Derivative Works; and
|
|
141
|
+
|
|
142
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
143
|
+
distribution, then any Derivative Works that You distribute must
|
|
144
|
+
include a readable copy of the attribution notices contained
|
|
145
|
+
within such NOTICE file, excluding those notices that do not
|
|
146
|
+
pertain to any part of the Derivative Works, in at least one
|
|
147
|
+
of the following places: within a NOTICE text file distributed
|
|
148
|
+
as part of the Derivative Works; within the Source form or
|
|
149
|
+
documentation, if provided along with the Derivative Works; or,
|
|
150
|
+
within a display generated by the Derivative Works, if and
|
|
151
|
+
wherever such third-party notices normally appear. The contents
|
|
152
|
+
of the NOTICE file are for informational purposes only and
|
|
153
|
+
do not modify the License. You may add Your own attribution
|
|
154
|
+
notices within Derivative Works that You distribute, alongside
|
|
155
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
156
|
+
that such additional attribution notices cannot be construed
|
|
157
|
+
as modifying the License.
|
|
158
|
+
|
|
159
|
+
You may add Your own copyright statement to Your modifications and
|
|
160
|
+
may provide additional or different license terms and conditions
|
|
161
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
162
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
163
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
164
|
+
the conditions stated in this License.
|
|
165
|
+
|
|
166
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
167
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
168
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
169
|
+
this License, without any additional terms or conditions.
|
|
170
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
171
|
+
the terms of any separate license agreement you may have executed
|
|
172
|
+
with Licensor regarding such Contributions.
|
|
173
|
+
|
|
174
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
175
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
176
|
+
except as required for reasonable and customary use in describing the
|
|
177
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
178
|
+
|
|
179
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
180
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
181
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
182
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
183
|
+
implied, including, without limitation, any warranties or conditions
|
|
184
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
185
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
186
|
+
appropriateness of using or redistributing the Work and assume any
|
|
187
|
+
risks associated with Your exercise of permissions under this License.
|
|
188
|
+
|
|
189
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
190
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
191
|
+
unless required by applicable law (such as deliberate and grossly
|
|
192
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
193
|
+
liable to You for damages, including any direct, indirect, special,
|
|
194
|
+
incidental, or consequential damages of any character arising as a
|
|
195
|
+
result of this License or out of the use or inability to use the
|
|
196
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
197
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
198
|
+
other commercial damages or losses), even if such Contributor
|
|
199
|
+
has been advised of the possibility of such damages.
|
|
200
|
+
|
|
201
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
202
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
203
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
204
|
+
or other liability obligations and/or rights consistent with this
|
|
205
|
+
License. However, in accepting such obligations, You may act only
|
|
206
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
207
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
208
|
+
defend, and hold each Contributor harmless for any liability
|
|
209
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
210
|
+
of your accepting any such warranty or additional liability.
|
|
211
|
+
|
|
212
|
+
END OF TERMS AND CONDITIONS
|
|
213
|
+
|
|
214
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
215
|
+
|
|
216
|
+
To apply the Apache License to your work, attach the following
|
|
217
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
218
|
+
replaced with your own identifying information. (Don't include
|
|
219
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
220
|
+
comment syntax for the file format. We also recommend that a
|
|
221
|
+
file or class name and description of purpose be included on the
|
|
222
|
+
same "printed page" as the copyright notice for easier
|
|
223
|
+
identification within third-party archives.
|
|
224
|
+
|
|
225
|
+
Copyright [yyyy] [name of copyright owner]
|
|
226
|
+
|
|
227
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
228
|
+
you may not use this file except in compliance with the License.
|
|
229
|
+
You may obtain a copy of the License at
|
|
230
|
+
|
|
231
|
+
https://www.apache.org/licenses/LICENSE-2.0
|
|
232
|
+
|
|
233
|
+
Unless required by applicable law or agreed to in writing, software
|
|
234
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
235
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
236
|
+
See the License for the specific language governing permissions and
|
|
237
|
+
limitations under the License.
|
data/LICENSE.txt
CHANGED
data/README.md
CHANGED
|
@@ -1,22 +1,23 @@
|
|
|
1
1
|
re2 [](https://github.com/mudge/re2/actions)
|
|
2
2
|
===
|
|
3
3
|
|
|
4
|
-
|
|
5
|
-
|
|
4
|
+
Ruby bindings to [RE2][], a "fast, safe, thread-friendly alternative to
|
|
5
|
+
backtracking regular expression engines like those used in PCRE, Perl, and
|
|
6
|
+
Python".
|
|
6
7
|
|
|
7
|
-
**Current version:** 2.
|
|
8
|
-
**Supported Ruby versions:** 2.7, 3.0, 3.1, 3.2
|
|
9
|
-
**Bundled
|
|
10
|
-
**Supported
|
|
8
|
+
**Current version:** 2.1.0
|
|
9
|
+
**Supported Ruby versions:** 2.6, 2.7, 3.0, 3.1, 3.2
|
|
10
|
+
**Bundled RE2 version:** libre2.11 (2023-09-01)
|
|
11
|
+
**Supported RE2 versions:** libre2.0 (< 2020-03-02), libre2.1 (2020-03-02), libre2.6 (2020-03-03), libre2.7 (2020-05-01), libre2.8 (2020-07-06), libre2.9 (2020-11-01), libre2.10 (2022-12-01), libre2.11 (2023-07-01)
|
|
11
12
|
|
|
12
13
|
Installation
|
|
13
14
|
------------
|
|
14
15
|
|
|
15
|
-
The gem comes bundled with a version of [
|
|
16
|
+
The gem comes bundled with a version of [RE2][] and will compile itself (and
|
|
16
17
|
any dependencies) on install. As compilation can take a while, precompiled
|
|
17
18
|
native gems are available for Linux, Windows and macOS.
|
|
18
19
|
|
|
19
|
-
In v2.0 and later, precompiled native gems are available for Ruby 2.
|
|
20
|
+
In v2.0 and later, precompiled native gems are available for Ruby 2.6 to 3.2
|
|
20
21
|
on these platforms:
|
|
21
22
|
|
|
22
23
|
- `aarch64-linux` (requires: glibc >= 2.29)
|
|
@@ -27,10 +28,10 @@ on these platforms:
|
|
|
27
28
|
- `x86_64-darwin`
|
|
28
29
|
- `x86_64-linux` (requires: glibc >= 2.17)
|
|
29
30
|
|
|
30
|
-
If you wish to opt out of using the bundled libraries, you will need
|
|
31
|
+
If you wish to opt out of using the bundled libraries, you will need RE2
|
|
31
32
|
installed as well as a C++ compiler such as [gcc][] (on Debian and Ubuntu, this
|
|
32
|
-
is provided by the [build-essential][] package). If you are using
|
|
33
|
-
recommend installing
|
|
33
|
+
is provided by the [build-essential][] package). If you are using macOS, I
|
|
34
|
+
recommend installing RE2 with [Homebrew][] by running the following:
|
|
34
35
|
|
|
35
36
|
$ brew install re2
|
|
36
37
|
|
|
@@ -38,7 +39,7 @@ If you are using Debian, you can install the [libre2-dev][] package like so:
|
|
|
38
39
|
|
|
39
40
|
$ sudo apt-get install libre2-dev
|
|
40
41
|
|
|
41
|
-
Recent versions of
|
|
42
|
+
Recent versions of RE2 require a compiler with C++14 support such as
|
|
42
43
|
[clang](http://clang.llvm.org/) 3.4 or [gcc](https://gcc.gnu.org/) 5.
|
|
43
44
|
|
|
44
45
|
If you are using a packaged Ruby distribution, make sure you also have the
|
|
@@ -47,13 +48,15 @@ on Debian and Ubuntu.
|
|
|
47
48
|
|
|
48
49
|
You can then install the library via RubyGems with `gem install re2 --platform=ruby --
|
|
49
50
|
--enable-system-libraries` or `gem install re2 --platform=ruby -- --enable-system-libraries
|
|
50
|
-
--with-re2-dir=/path/to/re2/prefix` if
|
|
51
|
+
--with-re2-dir=/path/to/re2/prefix` if RE2 is not installed in any of the
|
|
51
52
|
following default locations:
|
|
52
53
|
|
|
53
54
|
* `/usr/local`
|
|
54
55
|
* `/opt/homebrew`
|
|
55
56
|
* `/usr`
|
|
56
57
|
|
|
58
|
+
Alternatively, you can set the `RE2_USE_SYSTEM_LIBRARIES` environment variable instead of passing `--enable-system-libraries` to the `gem` command.
|
|
59
|
+
|
|
57
60
|
If you're using Bundler, you can use the
|
|
58
61
|
[`force_ruby_platform`](https://bundler.io/v2.3/man/gemfile.5.html#FORCE_RUBY_PLATFORM)
|
|
59
62
|
option in your Gemfile.
|
|
@@ -64,7 +67,7 @@ Documentation
|
|
|
64
67
|
Full documentation automatically generated from the latest version is
|
|
65
68
|
available at <http://mudge.name/re2/>.
|
|
66
69
|
|
|
67
|
-
Note that
|
|
70
|
+
Note that RE2's regular expression syntax differs from PCRE and Ruby's
|
|
68
71
|
built-in [`Regexp`][Regexp] library, see the [official syntax page][] for more
|
|
69
72
|
details.
|
|
70
73
|
|
|
@@ -190,6 +193,24 @@ end
|
|
|
190
193
|
# My name is Alice and I am 42 years old
|
|
191
194
|
```
|
|
192
195
|
|
|
196
|
+
Encoding
|
|
197
|
+
--------
|
|
198
|
+
|
|
199
|
+
Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be
|
|
200
|
+
returned in UTF-8 by default or ISO-8859-1 if the `:utf8` option for the
|
|
201
|
+
`RE2::Regexp` is set to false (any other encoding's behaviour is undefined).
|
|
202
|
+
|
|
203
|
+
For backward compatibility: re2 won't automatically convert string inputs to
|
|
204
|
+
the right encoding so this is the responsibility of the caller, e.g.
|
|
205
|
+
|
|
206
|
+
```ruby
|
|
207
|
+
# By default, RE2 will process patterns and text as UTF-8
|
|
208
|
+
RE2(non_utf8_pattern.encode("UTF-8")).match(non_utf8_text.encode("UTF-8"))
|
|
209
|
+
|
|
210
|
+
# If the :utf8 option is false, RE2 will process patterns and text as ISO-8859-1
|
|
211
|
+
RE2(non_latin1_pattern.encode("ISO-8859-1"), :utf8 => false).match(non_latin1_text.encode("ISO-8859-1"))
|
|
212
|
+
```
|
|
213
|
+
|
|
193
214
|
Features
|
|
194
215
|
--------
|
|
195
216
|
|
|
@@ -236,9 +257,9 @@ Contributions
|
|
|
236
257
|
* Thanks to [Jason Woods](https://github.com/driskell) who contributed the
|
|
237
258
|
original implementations of `RE2::MatchData#begin` and `RE2::MatchData#end`;
|
|
238
259
|
* Thanks to [Stefano Rivera](https://github.com/stefanor) who first contributed C++11 support;
|
|
239
|
-
* Thanks to [Stan Hu](https://github.com/stanhu) for reporting a bug with empty patterns and `RE2::Regexp#scan`, contributing support for libre2.11 (2023-07-01) and for vendoring
|
|
260
|
+
* Thanks to [Stan Hu](https://github.com/stanhu) for reporting a bug with empty patterns and `RE2::Regexp#scan`, contributing support for libre2.11 (2023-07-01) and for vendoring RE2 and abseil and compiling native gems in 2.0;
|
|
240
261
|
* Thanks to [Sebastian Reitenbach](https://github.com/buzzdeee) for reporting
|
|
241
|
-
the deprecation and removal of the `utf8` encoding option in
|
|
262
|
+
the deprecation and removal of the `utf8` encoding option in RE2;
|
|
242
263
|
* Thanks to [Sergio Medina](https://github.com/serch) for reporting a bug when
|
|
243
264
|
using `RE2::Scanner#scan` with an invalid regular expression;
|
|
244
265
|
* Thanks to [Pritam Baral](https://github.com/pritambaral) for contributed the
|
|
@@ -249,7 +270,19 @@ Contact
|
|
|
249
270
|
|
|
250
271
|
All issues and suggestions should go to [GitHub Issues](https://github.com/mudge/re2/issues).
|
|
251
272
|
|
|
252
|
-
|
|
273
|
+
License
|
|
274
|
+
-------
|
|
275
|
+
|
|
276
|
+
This library is licensed under the BSD 3-Clause License, see `LICENSE.txt`.
|
|
277
|
+
|
|
278
|
+
Dependencies
|
|
279
|
+
------------
|
|
280
|
+
|
|
281
|
+
The source code of [RE2][] is distributed in the `ruby` platform gem. This code is licensed under the BSD 3-Clause License, see `LICENSE-DEPENDENCIES.txt`.
|
|
282
|
+
|
|
283
|
+
The source code of [Abseil][] is distributed in the `ruby` platform gem. This code is licensed under the Apache License 2.0, see `LICENSE-DEPENDENCIES.txt`.
|
|
284
|
+
|
|
285
|
+
[RE2]: https://github.com/google/re2
|
|
253
286
|
[gcc]: http://gcc.gnu.org/
|
|
254
287
|
[ruby-dev]: http://packages.debian.org/ruby-dev
|
|
255
288
|
[build-essential]: http://packages.debian.org/build-essential
|
|
@@ -258,4 +291,4 @@ All issues and suggestions should go to [GitHub Issues](https://github.com/mudge
|
|
|
258
291
|
[Homebrew]: http://mxcl.github.com/homebrew
|
|
259
292
|
[libre2-dev]: http://packages.debian.org/search?keywords=libre2-dev
|
|
260
293
|
[official syntax page]: https://github.com/google/re2/wiki/Syntax
|
|
261
|
-
|
|
294
|
+
[Abseil]: https://abseil.io
|
data/ext/re2/re2.cc
CHANGED
|
@@ -39,18 +39,9 @@ using std::vector;
|
|
|
39
39
|
rb_enc_associate_index(_string, _enc); \
|
|
40
40
|
_string; \
|
|
41
41
|
})
|
|
42
|
-
#define ENCODED_STR_NEW2(str, length, str2) \
|
|
43
|
-
({ \
|
|
44
|
-
VALUE _string = rb_str_new(str, length); \
|
|
45
|
-
int _enc = rb_enc_get_index(str2); \
|
|
46
|
-
rb_enc_associate_index(_string, _enc); \
|
|
47
|
-
_string; \
|
|
48
|
-
})
|
|
49
42
|
#else
|
|
50
43
|
#define ENCODED_STR_NEW(str, length, encoding) \
|
|
51
44
|
rb_str_new((const char *)str, (long)length)
|
|
52
|
-
#define ENCODED_STR_NEW2(str, length, str2) \
|
|
53
|
-
rb_str_new((const char *)str, (long)length)
|
|
54
45
|
#endif
|
|
55
46
|
|
|
56
47
|
#ifdef HAVE_RB_STR_SUBLEN
|
|
@@ -284,6 +275,10 @@ static VALUE re2_scanner_rewind(VALUE self) {
|
|
|
284
275
|
* Scan the given text incrementally for matches, returning an array of
|
|
285
276
|
* matches on each subsequent call. Returns nil if no matches are found.
|
|
286
277
|
*
|
|
278
|
+
* Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be
|
|
279
|
+
* returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the
|
|
280
|
+
* RE2::Regexp is set to false (any other encoding's behaviour is undefined).
|
|
281
|
+
*
|
|
287
282
|
* @return [Array<String>] the matches.
|
|
288
283
|
* @example
|
|
289
284
|
* s = RE2::Regexp.new('(\w+)').scan("Foo bar baz")
|
|
@@ -312,7 +307,6 @@ static VALUE re2_scanner_scan(VALUE self) {
|
|
|
312
307
|
original_input_size = c->input->size();
|
|
313
308
|
|
|
314
309
|
for (i = 0; i < c->number_of_capturing_groups; i++) {
|
|
315
|
-
matches[i] = "";
|
|
316
310
|
argv[i] = &matches[i];
|
|
317
311
|
args[i] = &argv[i];
|
|
318
312
|
}
|
|
@@ -504,6 +498,10 @@ static VALUE re2_regexp_allocate(VALUE klass) {
|
|
|
504
498
|
/*
|
|
505
499
|
* Returns the array of matches.
|
|
506
500
|
*
|
|
501
|
+
* Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be
|
|
502
|
+
* returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the
|
|
503
|
+
* RE2::Regexp is set to false (any other encoding's behaviour is undefined).
|
|
504
|
+
*
|
|
507
505
|
* @return [Array<String, nil>] the array of matches
|
|
508
506
|
* @example
|
|
509
507
|
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
|
@@ -579,6 +577,10 @@ static VALUE re2_matchdata_named_match(const char* name, VALUE self) {
|
|
|
579
577
|
/*
|
|
580
578
|
* Retrieve zero, one or more matches by index or name.
|
|
581
579
|
*
|
|
580
|
+
* Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be
|
|
581
|
+
* returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the
|
|
582
|
+
* RE2::Regexp is set to false (any other encoding's behaviour is undefined).
|
|
583
|
+
*
|
|
582
584
|
* @return [Array<String, nil>, String, Boolean]
|
|
583
585
|
*
|
|
584
586
|
* @overload [](index)
|
|
@@ -646,6 +648,10 @@ static VALUE re2_matchdata_to_s(VALUE self) {
|
|
|
646
648
|
/*
|
|
647
649
|
* Returns a printable version of the match.
|
|
648
650
|
*
|
|
651
|
+
* Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be
|
|
652
|
+
* returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the
|
|
653
|
+
* RE2::Regexp is set to false (any other encoding's behaviour is undefined).
|
|
654
|
+
*
|
|
649
655
|
* @return [String] a printable version of the match
|
|
650
656
|
* @example
|
|
651
657
|
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
|
@@ -690,6 +696,10 @@ static VALUE re2_matchdata_inspect(VALUE self) {
|
|
|
690
696
|
/*
|
|
691
697
|
* Returns the array of submatches for pattern matching.
|
|
692
698
|
*
|
|
699
|
+
* Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be
|
|
700
|
+
* returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the
|
|
701
|
+
* RE2::Regexp is set to false (any other encoding's behaviour is undefined).
|
|
702
|
+
*
|
|
693
703
|
* @return [Array<String, nil>] the array of submatches
|
|
694
704
|
* @example
|
|
695
705
|
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
|
@@ -735,6 +745,10 @@ static VALUE re2_matchdata_deconstruct(VALUE self) {
|
|
|
735
745
|
* more keys than there are capturing groups. Given keys will populate the hash in
|
|
736
746
|
* order but an invalid name will cause the hash to be immediately returned.
|
|
737
747
|
*
|
|
748
|
+
* Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be
|
|
749
|
+
* returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the
|
|
750
|
+
* RE2::Regexp is set to false (any other encoding's behaviour is undefined).
|
|
751
|
+
*
|
|
738
752
|
* @return [Hash] a hash of capturing group names to submatches
|
|
739
753
|
* @param [Array<Symbol>, nil] keys an array of Symbol capturing group names or nil to return all names
|
|
740
754
|
* @example
|
|
@@ -866,6 +880,10 @@ static VALUE re2_regexp_initialize(int argc, VALUE *argv, VALUE self) {
|
|
|
866
880
|
/*
|
|
867
881
|
* Returns a printable version of the regular expression +re2+.
|
|
868
882
|
*
|
|
883
|
+
* Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be
|
|
884
|
+
* returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the
|
|
885
|
+
* RE2::Regexp is set to false (any other encoding's behaviour is undefined).
|
|
886
|
+
*
|
|
869
887
|
* @return [String] a printable version of the regular expression
|
|
870
888
|
* @example
|
|
871
889
|
* re2 = RE2::Regexp.new("woo?")
|
|
@@ -889,6 +907,10 @@ static VALUE re2_regexp_inspect(VALUE self) {
|
|
|
889
907
|
/*
|
|
890
908
|
* Returns a string version of the regular expression +re2+.
|
|
891
909
|
*
|
|
910
|
+
* Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be
|
|
911
|
+
* returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the
|
|
912
|
+
* RE2::Regexp is set to false (any other encoding's behaviour is undefined).
|
|
913
|
+
*
|
|
892
914
|
* @return [String] a string version of the regular expression
|
|
893
915
|
* @example
|
|
894
916
|
* re2 = RE2::Regexp.new("woo?")
|
|
@@ -1116,6 +1138,10 @@ static VALUE re2_regexp_error(VALUE self) {
|
|
|
1116
1138
|
* If the RE2 could not be created properly, returns
|
|
1117
1139
|
* the offending portion of the regexp otherwise returns nil.
|
|
1118
1140
|
*
|
|
1141
|
+
* Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be
|
|
1142
|
+
* returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the
|
|
1143
|
+
* RE2::Regexp is set to false (any other encoding's behaviour is undefined).
|
|
1144
|
+
*
|
|
1119
1145
|
* @return [String, nil] the offending portion of the regexp or nil
|
|
1120
1146
|
*/
|
|
1121
1147
|
static VALUE re2_regexp_error_arg(VALUE self) {
|
|
@@ -1212,6 +1238,10 @@ static VALUE re2_regexp_number_of_capturing_groups(VALUE self) {
|
|
|
1212
1238
|
/*
|
|
1213
1239
|
* Returns a hash of names to capturing indices of groups.
|
|
1214
1240
|
*
|
|
1241
|
+
* Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be
|
|
1242
|
+
* returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the
|
|
1243
|
+
* RE2::Regexp is set to false (any other encoding's behaviour is undefined).
|
|
1244
|
+
*
|
|
1215
1245
|
* @return [Hash] a hash of names to capturing indices
|
|
1216
1246
|
*/
|
|
1217
1247
|
static VALUE re2_regexp_named_capturing_groups(VALUE self) {
|
|
@@ -1242,16 +1272,23 @@ static VALUE re2_regexp_named_capturing_groups(VALUE self) {
|
|
|
1242
1272
|
* @return [Boolean, RE2::MatchData]
|
|
1243
1273
|
*
|
|
1244
1274
|
* @overload match(text)
|
|
1245
|
-
* Returns an {RE2::MatchData} containing the matching
|
|
1246
|
-
*
|
|
1247
|
-
*
|
|
1275
|
+
* Returns an {RE2::MatchData} containing the matching pattern and all
|
|
1276
|
+
* subpatterns resulting from looking for the regexp in +text+ if the pattern
|
|
1277
|
+
* contains capturing groups.
|
|
1278
|
+
*
|
|
1279
|
+
* Returns either true or false indicating whether a successful match was
|
|
1280
|
+
* made if the pattern contains no capturing groups.
|
|
1248
1281
|
*
|
|
1249
1282
|
* @param [String] text the text to search
|
|
1250
|
-
* @return [RE2::MatchData] the
|
|
1283
|
+
* @return [RE2::MatchData] if the pattern contains capturing groups
|
|
1284
|
+
* @return [Boolean] if the pattern does not contain capturing groups
|
|
1251
1285
|
* @raise [NoMemoryError] if there was not enough memory to allocate the matches
|
|
1252
|
-
* @example
|
|
1286
|
+
* @example Matching with capturing groups
|
|
1253
1287
|
* r = RE2::Regexp.new('w(o)(o)')
|
|
1254
1288
|
* r.match('woo') #=> #<RE2::MatchData "woo" 1:"o" 2:"o">
|
|
1289
|
+
* @example Matching without capturing groups
|
|
1290
|
+
* r = RE2::Regexp.new('woo')
|
|
1291
|
+
* r.match('woo') #=> true
|
|
1255
1292
|
*
|
|
1256
1293
|
* @overload match(text, 0)
|
|
1257
1294
|
* Returns either true or false indicating whether a
|
|
@@ -1390,6 +1427,10 @@ static VALUE re2_regexp_scan(VALUE self, VALUE text) {
|
|
|
1390
1427
|
* Returns a copy of +str+ with the first occurrence +pattern+
|
|
1391
1428
|
* replaced with +rewrite+.
|
|
1392
1429
|
*
|
|
1430
|
+
* Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be
|
|
1431
|
+
* returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the
|
|
1432
|
+
* RE2::Regexp is set to false (any other encoding's behaviour is undefined).
|
|
1433
|
+
*
|
|
1393
1434
|
* @param [String] str the string to modify
|
|
1394
1435
|
* @param [String, RE2::Regexp] pattern a regexp matching text to be replaced
|
|
1395
1436
|
* @param [String] rewrite the string to replace with
|
|
@@ -1404,7 +1445,9 @@ static VALUE re2_Replace(VALUE self, VALUE str, VALUE pattern,
|
|
|
1404
1445
|
UNUSED(self);
|
|
1405
1446
|
re2_pattern *p;
|
|
1406
1447
|
|
|
1407
|
-
/*
|
|
1448
|
+
/* Take a copy of str so it can be modified in-place by
|
|
1449
|
+
* RE2::Replace.
|
|
1450
|
+
*/
|
|
1408
1451
|
string str_as_string(StringValuePtr(str));
|
|
1409
1452
|
|
|
1410
1453
|
/* Do the replacement. */
|
|
@@ -1418,8 +1461,8 @@ static VALUE re2_Replace(VALUE self, VALUE str, VALUE pattern,
|
|
|
1418
1461
|
RE2::Replace(&str_as_string, StringValuePtr(pattern),
|
|
1419
1462
|
StringValuePtr(rewrite));
|
|
1420
1463
|
|
|
1421
|
-
return
|
|
1422
|
-
|
|
1464
|
+
return ENCODED_STR_NEW(str_as_string.data(), str_as_string.size(),
|
|
1465
|
+
"UTF-8");
|
|
1423
1466
|
}
|
|
1424
1467
|
|
|
1425
1468
|
}
|
|
@@ -1427,6 +1470,10 @@ static VALUE re2_Replace(VALUE self, VALUE str, VALUE pattern,
|
|
|
1427
1470
|
/*
|
|
1428
1471
|
* Return a copy of +str+ with +pattern+ replaced by +rewrite+.
|
|
1429
1472
|
*
|
|
1473
|
+
* Note RE2 only supports UTF-8 and ISO-8859-1 encoding so strings will be
|
|
1474
|
+
* returned in UTF-8 by default or ISO-8859-1 if the :utf8 option for the
|
|
1475
|
+
* RE2::Regexp is set to false (any other encoding's behaviour is undefined).
|
|
1476
|
+
*
|
|
1430
1477
|
* @param [String] str the string to modify
|
|
1431
1478
|
* @param [String, RE2::Regexp] pattern a regexp matching text to be replaced
|
|
1432
1479
|
* @param [String] rewrite the string to replace with
|
|
@@ -1440,7 +1487,9 @@ static VALUE re2_GlobalReplace(VALUE self, VALUE str, VALUE pattern,
|
|
|
1440
1487
|
VALUE rewrite) {
|
|
1441
1488
|
UNUSED(self);
|
|
1442
1489
|
|
|
1443
|
-
/*
|
|
1490
|
+
/* Take a copy of str so it can be modified in-place by
|
|
1491
|
+
* RE2::GlobalReplace.
|
|
1492
|
+
*/
|
|
1444
1493
|
re2_pattern *p;
|
|
1445
1494
|
string str_as_string(StringValuePtr(str));
|
|
1446
1495
|
|
|
@@ -1455,8 +1504,8 @@ static VALUE re2_GlobalReplace(VALUE self, VALUE str, VALUE pattern,
|
|
|
1455
1504
|
RE2::GlobalReplace(&str_as_string, StringValuePtr(pattern),
|
|
1456
1505
|
StringValuePtr(rewrite));
|
|
1457
1506
|
|
|
1458
|
-
return
|
|
1459
|
-
|
|
1507
|
+
return ENCODED_STR_NEW(str_as_string.data(), str_as_string.size(),
|
|
1508
|
+
"UTF-8");
|
|
1460
1509
|
}
|
|
1461
1510
|
}
|
|
1462
1511
|
|
|
@@ -1579,11 +1628,12 @@ static VALUE re2_set_initialize(int argc, VALUE *argv, VALUE self) {
|
|
|
1579
1628
|
* set.add("def") #=> 1
|
|
1580
1629
|
*/
|
|
1581
1630
|
static VALUE re2_set_add(VALUE self, VALUE pattern) {
|
|
1582
|
-
|
|
1631
|
+
StringValue(pattern);
|
|
1583
1632
|
re2::StringPiece regex(RSTRING_PTR(pattern), RSTRING_LEN(pattern));
|
|
1584
1633
|
std::string err;
|
|
1585
1634
|
re2_set *s;
|
|
1586
1635
|
Data_Get_Struct(self, re2_set, s);
|
|
1636
|
+
|
|
1587
1637
|
int index = s->set->Add(regex, &err);
|
|
1588
1638
|
if (index < 0) {
|
|
1589
1639
|
rb_raise(rb_eArgError, "str rejected by RE2::Set->Add(): %s", err.c_str());
|
|
@@ -1669,7 +1719,8 @@ static VALUE re2_set_match(int argc, VALUE *argv, VALUE self) {
|
|
|
1669
1719
|
VALUE str, options, exception_option;
|
|
1670
1720
|
bool raise_exception = true;
|
|
1671
1721
|
rb_scan_args(argc, argv, "11", &str, &options);
|
|
1672
|
-
|
|
1722
|
+
|
|
1723
|
+
StringValue(str);
|
|
1673
1724
|
re2::StringPiece data(RSTRING_PTR(str), RSTRING_LEN(str));
|
|
1674
1725
|
std::vector<int> v;
|
|
1675
1726
|
re2_set *s;
|
data/lib/re2/version.rb
CHANGED