1 | #Region "Microsoft.VisualBasic::a0fcd8f9dc61e9692270663703b1ba91, Microsoft.VisualBasic.Core\Language\Language\Python\Regexp.vb" |
2 | |
3 | ' Author: |
4 | ' |
5 | ' asuka (amethyst.asuka@gcmodeller.org) |
6 | ' xie (genetics@smrucc.org) |
7 | ' xieguigang (xie.guigang@live.com) |
8 | ' |
9 | ' Copyright (c) 2018 GPL3 Licensed |
10 | ' |
11 | ' |
12 | ' GNU GENERAL PUBLIC LICENSE (GPL3) |
13 | ' |
14 | ' |
15 | ' This program is free software: you can redistribute it and/or modify |
16 | ' it under the terms of the GNU General Public License as published by |
17 | ' the Free Software Foundation, either version 3 of the License, or |
18 | ' (at your option) any later version. |
19 | ' |
20 | ' This program is distributed in the hope that it will be useful, |
21 | ' but WITHOUT ANY WARRANTY; without even the implied warranty of |
22 | ' MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
23 | ' GNU General Public License for more details. |
24 | ' |
25 | ' You should have received a copy of the GNU General Public License |
26 | ' along with this program. If not, see <http://www.gnu.org/licenses/>. |
27 | |
28 | |
29 | |
30 | ' /********************************************************************************/ |
31 | |
32 | ' Summaries: |
33 | |
34 | ' Module re |
35 | ' |
36 | ' Function: __trimComment, FindAll |
37 | ' Structure Match |
38 | ' |
39 | ' Constructor: (+1 Overloads) Sub New |
40 | ' Function: ToString |
41 | ' |
42 | ' |
43 | ' |
44 | ' |
45 | ' /********************************************************************************/ |
46 | |
47 | #End Region |
48 | |
49 | Imports System.Text.RegularExpressions |
50 | Imports Microsoft.VisualBasic.Linq |
51 | |
52 | Namespace Language.Python |
53 | |
54 | ''' <summary> |
55 | ''' This module provides regular expression matching operations similar to those found in Perl. ``re`` module in the python language. |
56 | ''' </summary> |
57 | Public Module re |
58 | |
59 | Public Structure Match |
60 | Private __raw As System.Text.RegularExpressions.Match |
61 | |
62 | Friend Sub New(m As System.Text.RegularExpressions.Match) |
63 | __raw = m |
64 | End Sub |
65 | |
66 | Default Public ReadOnly Property Value(index%) As String |
67 | Get |
68 | If index < 0 Then |
69 | index = __raw.Groups.Count + index% |
70 | End If |
71 | |
72 | Return __raw.Groups.Item(index%).Value |
73 | End Get |
74 | End Property |
75 | |
76 | Public Shared Narrowing Operator CType(m As Match) As String |
77 | Return m.__raw.Value |
78 | End Operator |
79 | |
80 | ''' <summary> |
81 | ''' <see cref="System.Text.RegularExpressions.Match.Value"/> |
82 | ''' </summary> |
83 | ''' <returns></returns> |
84 | Public Overrides Function ToString() As String |
85 | Return __raw.Value |
86 | End Function |
87 | End Structure |
88 | |
89 | ''' <summary> |
90 | ''' Return all non-overlapping matches of pattern in string, as a list of strings. The string is scanned left-to-right, and matches are returned in the order found. |
91 | ''' If one or more groups are present in the pattern, return a list of groups; this will be a list of tuples if the pattern has more than one group. |
92 | ''' Empty matches are included in the result unless they touch the beginning of another match. |
93 | ''' </summary> |
94 | ''' <param name="pattern">这个会首先被分行然后去除掉python注释</param> |
95 | ''' <param name="input"></param> |
96 | ''' <param name="options"></param> |
97 | ''' <returns></returns> |
98 | Public Function FindAll(pattern$, input$, Optional options As RegexOptions = RegexOptions.None) As Array(Of Match) |
99 | Dim tokens As String() = pattern.Trim _ |
100 | .LineTokens _ |
101 | .Select(AddressOf __trimComment) _ |
102 | .Where(Function(s) Not String.IsNullOrEmpty(s)) _ |
103 | .ToArray |
104 | pattern = String.Join("", tokens) |
105 | |
106 | Dim ms As MatchCollection = |
107 | Regex.Matches(input, pattern, options) |
108 | Dim mlist As IEnumerable(Of Match) = |
109 | ms.Count _ |
110 | .Sequence _ |
111 | .Select(Function(i) New Match(ms(i))) |
112 | |
113 | Return New Array(Of Match)(mlist) |
114 | End Function |
115 | |
116 | ''' <summary> |
117 | ''' 假设所有的注释都是由#和一个空格开始起始的 ``# `` |
118 | ''' </summary> |
119 | ''' <param name="s"></param> |
120 | ''' <returns></returns> |
121 | Private Function __trimComment(s As String) As String |
122 | s = s.Trim |
123 | |
124 | If s.StartsWith("# ") Then Return "" ' 整行都是注释 |
125 | |
126 | Dim i As Integer = s.IndexOf("# ") |
127 | |
128 | If i > -1 Then |
129 | s = s.Substring(0, i).Trim |
130 | End If |
131 | |
132 | Return s |
133 | End Function |
134 | End Module |
135 | End Namespace |