Show More
@@ -1,510 +1,511 b'' | |||||
1 | # -*- coding: utf-8 -*- |
|
1 | # -*- coding: utf-8 -*- | |
2 | """ |
|
2 | """ | |
3 | Defines a variety of Pygments lexers for highlighting IPython code. |
|
3 | Defines a variety of Pygments lexers for highlighting IPython code. | |
4 |
|
4 | |||
5 | This includes: |
|
5 | This includes: | |
6 |
|
6 | |||
7 | IPythonLexer, IPython3Lexer |
|
7 | IPythonLexer, IPython3Lexer | |
8 | Lexers for pure IPython (python + magic/shell commands) |
|
8 | Lexers for pure IPython (python + magic/shell commands) | |
9 |
|
9 | |||
10 | IPythonPartialTracebackLexer, IPythonTracebackLexer |
|
10 | IPythonPartialTracebackLexer, IPythonTracebackLexer | |
11 | Supports 2.x and 3.x via keyword `python3`. The partial traceback |
|
11 | Supports 2.x and 3.x via keyword `python3`. The partial traceback | |
12 | lexer reads everything but the Python code appearing in a traceback. |
|
12 | lexer reads everything but the Python code appearing in a traceback. | |
13 | The full lexer combines the partial lexer with an IPython lexer. |
|
13 | The full lexer combines the partial lexer with an IPython lexer. | |
14 |
|
14 | |||
15 | IPythonConsoleLexer |
|
15 | IPythonConsoleLexer | |
16 | A lexer for IPython console sessions, with support for tracebacks. |
|
16 | A lexer for IPython console sessions, with support for tracebacks. | |
17 |
|
17 | |||
18 | IPyLexer |
|
18 | IPyLexer | |
19 | A friendly lexer which examines the first line of text and from it, |
|
19 | A friendly lexer which examines the first line of text and from it, | |
20 | decides whether to use an IPython lexer or an IPython console lexer. |
|
20 | decides whether to use an IPython lexer or an IPython console lexer. | |
21 | This is probably the only lexer that needs to be explicitly added |
|
21 | This is probably the only lexer that needs to be explicitly added | |
22 | to Pygments. |
|
22 | to Pygments. | |
23 |
|
23 | |||
24 | """ |
|
24 | """ | |
25 | #----------------------------------------------------------------------------- |
|
25 | #----------------------------------------------------------------------------- | |
26 | # Copyright (c) 2013, the IPython Development Team. |
|
26 | # Copyright (c) 2013, the IPython Development Team. | |
27 | # |
|
27 | # | |
28 | # Distributed under the terms of the Modified BSD License. |
|
28 | # Distributed under the terms of the Modified BSD License. | |
29 | # |
|
29 | # | |
30 | # The full license is in the file COPYING.txt, distributed with this software. |
|
30 | # The full license is in the file COPYING.txt, distributed with this software. | |
31 | #----------------------------------------------------------------------------- |
|
31 | #----------------------------------------------------------------------------- | |
32 |
|
32 | |||
33 | # Standard library |
|
33 | # Standard library | |
34 | import re |
|
34 | import re | |
35 |
|
35 | |||
36 | # Third party |
|
36 | # Third party | |
37 | from pygments.lexers import BashLexer, PythonLexer, Python3Lexer |
|
37 | from pygments.lexers import BashLexer, PythonLexer, Python3Lexer | |
38 | from pygments.lexer import ( |
|
38 | from pygments.lexer import ( | |
39 | Lexer, DelegatingLexer, RegexLexer, do_insertions, bygroups, using, |
|
39 | Lexer, DelegatingLexer, RegexLexer, do_insertions, bygroups, using, | |
40 | ) |
|
40 | ) | |
41 | from pygments.token import ( |
|
41 | from pygments.token import ( | |
42 | Comment, Generic, Keyword, Literal, Name, Operator, Other, Text, Error, |
|
42 | Comment, Generic, Keyword, Literal, Name, Operator, Other, Text, Error, | |
43 | ) |
|
43 | ) | |
44 | from pygments.util import get_bool_opt |
|
44 | from pygments.util import get_bool_opt | |
45 |
|
45 | |||
46 | # Local |
|
46 | # Local | |
47 |
|
47 | |||
48 | line_re = re.compile('.*?\n') |
|
48 | line_re = re.compile('.*?\n') | |
49 |
|
49 | |||
50 | __all__ = ['build_ipy_lexer', 'IPython3Lexer', 'IPythonLexer', |
|
50 | __all__ = ['build_ipy_lexer', 'IPython3Lexer', 'IPythonLexer', | |
51 | 'IPythonPartialTracebackLexer', 'IPythonTracebackLexer', |
|
51 | 'IPythonPartialTracebackLexer', 'IPythonTracebackLexer', | |
52 | 'IPythonConsoleLexer', 'IPyLexer'] |
|
52 | 'IPythonConsoleLexer', 'IPyLexer'] | |
53 |
|
53 | |||
54 | ipython_tokens = [ |
|
54 | ipython_tokens = [ | |
55 | (r"(?s)(\s*)(%%)(\w+)(.*)", bygroups(Text, Operator, Keyword, Text)), |
|
55 | (r"(?s)(\s*)(%%)(\w+)(.*)", bygroups(Text, Operator, Keyword, Text)), | |
56 | (r'(?s)(^\s*)(%%!)([^\n]*\n)(.*)', bygroups(Text, Operator, Text, using(BashLexer))), |
|
56 | (r'(?s)(^\s*)(%%!)([^\n]*\n)(.*)', bygroups(Text, Operator, Text, using(BashLexer))), | |
57 | (r"(%%?)(\w+)(\?\??)$", bygroups(Operator, Keyword, Operator)), |
|
57 | (r"(%%?)(\w+)(\?\??)$", bygroups(Operator, Keyword, Operator)), | |
58 | (r"\b(\?\??)(\s*)$", bygroups(Operator, Text)), |
|
58 | (r"\b(\?\??)(\s*)$", bygroups(Operator, Text)), | |
59 | (r'(%)(sx|sc|system)(.*)(\n)', bygroups(Operator, Keyword, |
|
59 | (r'(%)(sx|sc|system)(.*)(\n)', bygroups(Operator, Keyword, | |
60 | using(BashLexer), Text)), |
|
60 | using(BashLexer), Text)), | |
61 | (r'(%)(\w+)(.*\n)', bygroups(Operator, Keyword, Text)), |
|
61 | (r'(%)(\w+)(.*\n)', bygroups(Operator, Keyword, Text)), | |
62 | (r'^(!!)(.+)(\n)', bygroups(Operator, using(BashLexer), Text)), |
|
62 | (r'^(!!)(.+)(\n)', bygroups(Operator, using(BashLexer), Text)), | |
63 | (r'(!)(?!=)(.+)(\n)', bygroups(Operator, using(BashLexer), Text)), |
|
63 | (r'(!)(?!=)(.+)(\n)', bygroups(Operator, using(BashLexer), Text)), | |
64 | (r'^(\s*)(\?\??)(\s*%{0,2}[\w\.\*]*)', bygroups(Text, Operator, Text)), |
|
64 | (r'^(\s*)(\?\??)(\s*%{0,2}[\w\.\*]*)', bygroups(Text, Operator, Text)), | |
|
65 | (r'(\s*%{0,2}[\w\.\*]*)(\?\??)(\s*)$', bygroups(Text, Operator, Text)), | |||
65 | ] |
|
66 | ] | |
66 |
|
67 | |||
67 | def build_ipy_lexer(python3): |
|
68 | def build_ipy_lexer(python3): | |
68 | """Builds IPython lexers depending on the value of `python3`. |
|
69 | """Builds IPython lexers depending on the value of `python3`. | |
69 |
|
70 | |||
70 | The lexer inherits from an appropriate Python lexer and then adds |
|
71 | The lexer inherits from an appropriate Python lexer and then adds | |
71 | information about IPython specific keywords (i.e. magic commands, |
|
72 | information about IPython specific keywords (i.e. magic commands, | |
72 | shell commands, etc.) |
|
73 | shell commands, etc.) | |
73 |
|
74 | |||
74 | Parameters |
|
75 | Parameters | |
75 | ---------- |
|
76 | ---------- | |
76 | python3 : bool |
|
77 | python3 : bool | |
77 | If `True`, then build an IPython lexer from a Python 3 lexer. |
|
78 | If `True`, then build an IPython lexer from a Python 3 lexer. | |
78 |
|
79 | |||
79 | """ |
|
80 | """ | |
80 | # It would be nice to have a single IPython lexer class which takes |
|
81 | # It would be nice to have a single IPython lexer class which takes | |
81 | # a boolean `python3`. But since there are two Python lexer classes, |
|
82 | # a boolean `python3`. But since there are two Python lexer classes, | |
82 | # we will also have two IPython lexer classes. |
|
83 | # we will also have two IPython lexer classes. | |
83 | if python3: |
|
84 | if python3: | |
84 | PyLexer = Python3Lexer |
|
85 | PyLexer = Python3Lexer | |
85 | clsname = 'IPython3Lexer' |
|
86 | clsname = 'IPython3Lexer' | |
86 | name = 'IPython3' |
|
87 | name = 'IPython3' | |
87 | aliases = ['ipython3'] |
|
88 | aliases = ['ipython3'] | |
88 | doc = """IPython3 Lexer""" |
|
89 | doc = """IPython3 Lexer""" | |
89 | else: |
|
90 | else: | |
90 | PyLexer = PythonLexer |
|
91 | PyLexer = PythonLexer | |
91 | clsname = 'IPythonLexer' |
|
92 | clsname = 'IPythonLexer' | |
92 | name = 'IPython' |
|
93 | name = 'IPython' | |
93 | aliases = ['ipython2', 'ipython'] |
|
94 | aliases = ['ipython2', 'ipython'] | |
94 | doc = """IPython Lexer""" |
|
95 | doc = """IPython Lexer""" | |
95 |
|
96 | |||
96 | tokens = PyLexer.tokens.copy() |
|
97 | tokens = PyLexer.tokens.copy() | |
97 | tokens['root'] = ipython_tokens + tokens['root'] |
|
98 | tokens['root'] = ipython_tokens + tokens['root'] | |
98 |
|
99 | |||
99 | attrs = {'name': name, 'aliases': aliases, 'filenames': [], |
|
100 | attrs = {'name': name, 'aliases': aliases, 'filenames': [], | |
100 | '__doc__': doc, 'tokens': tokens} |
|
101 | '__doc__': doc, 'tokens': tokens} | |
101 |
|
102 | |||
102 | return type(name, (PyLexer,), attrs) |
|
103 | return type(name, (PyLexer,), attrs) | |
103 |
|
104 | |||
104 |
|
105 | |||
105 | IPython3Lexer = build_ipy_lexer(python3=True) |
|
106 | IPython3Lexer = build_ipy_lexer(python3=True) | |
106 | IPythonLexer = build_ipy_lexer(python3=False) |
|
107 | IPythonLexer = build_ipy_lexer(python3=False) | |
107 |
|
108 | |||
108 |
|
109 | |||
109 | class IPythonPartialTracebackLexer(RegexLexer): |
|
110 | class IPythonPartialTracebackLexer(RegexLexer): | |
110 | """ |
|
111 | """ | |
111 | Partial lexer for IPython tracebacks. |
|
112 | Partial lexer for IPython tracebacks. | |
112 |
|
113 | |||
113 | Handles all the non-python output. This works for both Python 2.x and 3.x. |
|
114 | Handles all the non-python output. This works for both Python 2.x and 3.x. | |
114 |
|
115 | |||
115 | """ |
|
116 | """ | |
116 | name = 'IPython Partial Traceback' |
|
117 | name = 'IPython Partial Traceback' | |
117 |
|
118 | |||
118 | tokens = { |
|
119 | tokens = { | |
119 | 'root': [ |
|
120 | 'root': [ | |
120 | # Tracebacks for syntax errors have a different style. |
|
121 | # Tracebacks for syntax errors have a different style. | |
121 | # For both types of tracebacks, we mark the first line with |
|
122 | # For both types of tracebacks, we mark the first line with | |
122 | # Generic.Traceback. For syntax errors, we mark the filename |
|
123 | # Generic.Traceback. For syntax errors, we mark the filename | |
123 | # as we mark the filenames for non-syntax tracebacks. |
|
124 | # as we mark the filenames for non-syntax tracebacks. | |
124 | # |
|
125 | # | |
125 | # These two regexps define how IPythonConsoleLexer finds a |
|
126 | # These two regexps define how IPythonConsoleLexer finds a | |
126 | # traceback. |
|
127 | # traceback. | |
127 | # |
|
128 | # | |
128 | ## Non-syntax traceback |
|
129 | ## Non-syntax traceback | |
129 | (r'^(\^C)?(-+\n)', bygroups(Error, Generic.Traceback)), |
|
130 | (r'^(\^C)?(-+\n)', bygroups(Error, Generic.Traceback)), | |
130 | ## Syntax traceback |
|
131 | ## Syntax traceback | |
131 | (r'^( File)(.*)(, line )(\d+\n)', |
|
132 | (r'^( File)(.*)(, line )(\d+\n)', | |
132 | bygroups(Generic.Traceback, Name.Namespace, |
|
133 | bygroups(Generic.Traceback, Name.Namespace, | |
133 | Generic.Traceback, Literal.Number.Integer)), |
|
134 | Generic.Traceback, Literal.Number.Integer)), | |
134 |
|
135 | |||
135 | # (Exception Identifier)(Whitespace)(Traceback Message) |
|
136 | # (Exception Identifier)(Whitespace)(Traceback Message) | |
136 | (r'(?u)(^[^\d\W]\w*)(\s*)(Traceback.*?\n)', |
|
137 | (r'(?u)(^[^\d\W]\w*)(\s*)(Traceback.*?\n)', | |
137 | bygroups(Name.Exception, Generic.Whitespace, Text)), |
|
138 | bygroups(Name.Exception, Generic.Whitespace, Text)), | |
138 | # (Module/Filename)(Text)(Callee)(Function Signature) |
|
139 | # (Module/Filename)(Text)(Callee)(Function Signature) | |
139 | # Better options for callee and function signature? |
|
140 | # Better options for callee and function signature? | |
140 | (r'(.*)( in )(.*)(\(.*\)\n)', |
|
141 | (r'(.*)( in )(.*)(\(.*\)\n)', | |
141 | bygroups(Name.Namespace, Text, Name.Entity, Name.Tag)), |
|
142 | bygroups(Name.Namespace, Text, Name.Entity, Name.Tag)), | |
142 | # Regular line: (Whitespace)(Line Number)(Python Code) |
|
143 | # Regular line: (Whitespace)(Line Number)(Python Code) | |
143 | (r'(\s*?)(\d+)(.*?\n)', |
|
144 | (r'(\s*?)(\d+)(.*?\n)', | |
144 | bygroups(Generic.Whitespace, Literal.Number.Integer, Other)), |
|
145 | bygroups(Generic.Whitespace, Literal.Number.Integer, Other)), | |
145 | # Emphasized line: (Arrow)(Line Number)(Python Code) |
|
146 | # Emphasized line: (Arrow)(Line Number)(Python Code) | |
146 | # Using Exception token so arrow color matches the Exception. |
|
147 | # Using Exception token so arrow color matches the Exception. | |
147 | (r'(-*>?\s?)(\d+)(.*?\n)', |
|
148 | (r'(-*>?\s?)(\d+)(.*?\n)', | |
148 | bygroups(Name.Exception, Literal.Number.Integer, Other)), |
|
149 | bygroups(Name.Exception, Literal.Number.Integer, Other)), | |
149 | # (Exception Identifier)(Message) |
|
150 | # (Exception Identifier)(Message) | |
150 | (r'(?u)(^[^\d\W]\w*)(:.*?\n)', |
|
151 | (r'(?u)(^[^\d\W]\w*)(:.*?\n)', | |
151 | bygroups(Name.Exception, Text)), |
|
152 | bygroups(Name.Exception, Text)), | |
152 | # Tag everything else as Other, will be handled later. |
|
153 | # Tag everything else as Other, will be handled later. | |
153 | (r'.*\n', Other), |
|
154 | (r'.*\n', Other), | |
154 | ], |
|
155 | ], | |
155 | } |
|
156 | } | |
156 |
|
157 | |||
157 |
|
158 | |||
158 | class IPythonTracebackLexer(DelegatingLexer): |
|
159 | class IPythonTracebackLexer(DelegatingLexer): | |
159 | """ |
|
160 | """ | |
160 | IPython traceback lexer. |
|
161 | IPython traceback lexer. | |
161 |
|
162 | |||
162 | For doctests, the tracebacks can be snipped as much as desired with the |
|
163 | For doctests, the tracebacks can be snipped as much as desired with the | |
163 | exception to the lines that designate a traceback. For non-syntax error |
|
164 | exception to the lines that designate a traceback. For non-syntax error | |
164 | tracebacks, this is the line of hyphens. For syntax error tracebacks, |
|
165 | tracebacks, this is the line of hyphens. For syntax error tracebacks, | |
165 | this is the line which lists the File and line number. |
|
166 | this is the line which lists the File and line number. | |
166 |
|
167 | |||
167 | """ |
|
168 | """ | |
168 | # The lexer inherits from DelegatingLexer. The "root" lexer is an |
|
169 | # The lexer inherits from DelegatingLexer. The "root" lexer is an | |
169 | # appropriate IPython lexer, which depends on the value of the boolean |
|
170 | # appropriate IPython lexer, which depends on the value of the boolean | |
170 | # `python3`. First, we parse with the partial IPython traceback lexer. |
|
171 | # `python3`. First, we parse with the partial IPython traceback lexer. | |
171 | # Then, any code marked with the "Other" token is delegated to the root |
|
172 | # Then, any code marked with the "Other" token is delegated to the root | |
172 | # lexer. |
|
173 | # lexer. | |
173 | # |
|
174 | # | |
174 | name = 'IPython Traceback' |
|
175 | name = 'IPython Traceback' | |
175 | aliases = ['ipythontb'] |
|
176 | aliases = ['ipythontb'] | |
176 |
|
177 | |||
177 | def __init__(self, **options): |
|
178 | def __init__(self, **options): | |
178 | self.python3 = get_bool_opt(options, 'python3', False) |
|
179 | self.python3 = get_bool_opt(options, 'python3', False) | |
179 | if self.python3: |
|
180 | if self.python3: | |
180 | self.aliases = ['ipython3tb'] |
|
181 | self.aliases = ['ipython3tb'] | |
181 | else: |
|
182 | else: | |
182 | self.aliases = ['ipython2tb', 'ipythontb'] |
|
183 | self.aliases = ['ipython2tb', 'ipythontb'] | |
183 |
|
184 | |||
184 | if self.python3: |
|
185 | if self.python3: | |
185 | IPyLexer = IPython3Lexer |
|
186 | IPyLexer = IPython3Lexer | |
186 | else: |
|
187 | else: | |
187 | IPyLexer = IPythonLexer |
|
188 | IPyLexer = IPythonLexer | |
188 |
|
189 | |||
189 | DelegatingLexer.__init__(self, IPyLexer, |
|
190 | DelegatingLexer.__init__(self, IPyLexer, | |
190 | IPythonPartialTracebackLexer, **options) |
|
191 | IPythonPartialTracebackLexer, **options) | |
191 |
|
192 | |||
192 | class IPythonConsoleLexer(Lexer): |
|
193 | class IPythonConsoleLexer(Lexer): | |
193 | """ |
|
194 | """ | |
194 | An IPython console lexer for IPython code-blocks and doctests, such as: |
|
195 | An IPython console lexer for IPython code-blocks and doctests, such as: | |
195 |
|
196 | |||
196 | .. code-block:: rst |
|
197 | .. code-block:: rst | |
197 |
|
198 | |||
198 | .. code-block:: ipythonconsole |
|
199 | .. code-block:: ipythonconsole | |
199 |
|
200 | |||
200 | In [1]: a = 'foo' |
|
201 | In [1]: a = 'foo' | |
201 |
|
202 | |||
202 | In [2]: a |
|
203 | In [2]: a | |
203 | Out[2]: 'foo' |
|
204 | Out[2]: 'foo' | |
204 |
|
205 | |||
205 | In [3]: print a |
|
206 | In [3]: print a | |
206 | foo |
|
207 | foo | |
207 |
|
208 | |||
208 | In [4]: 1 / 0 |
|
209 | In [4]: 1 / 0 | |
209 |
|
210 | |||
210 |
|
211 | |||
211 | Support is also provided for IPython exceptions: |
|
212 | Support is also provided for IPython exceptions: | |
212 |
|
213 | |||
213 | .. code-block:: rst |
|
214 | .. code-block:: rst | |
214 |
|
215 | |||
215 | .. code-block:: ipythonconsole |
|
216 | .. code-block:: ipythonconsole | |
216 |
|
217 | |||
217 | In [1]: raise Exception |
|
218 | In [1]: raise Exception | |
218 |
|
219 | |||
219 | --------------------------------------------------------------------------- |
|
220 | --------------------------------------------------------------------------- | |
220 | Exception Traceback (most recent call last) |
|
221 | Exception Traceback (most recent call last) | |
221 | <ipython-input-1-fca2ab0ca76b> in <module>() |
|
222 | <ipython-input-1-fca2ab0ca76b> in <module>() | |
222 | ----> 1 raise Exception |
|
223 | ----> 1 raise Exception | |
223 |
|
224 | |||
224 | Exception: |
|
225 | Exception: | |
225 |
|
226 | |||
226 | """ |
|
227 | """ | |
227 | name = 'IPython console session' |
|
228 | name = 'IPython console session' | |
228 | aliases = ['ipythonconsole'] |
|
229 | aliases = ['ipythonconsole'] | |
229 | mimetypes = ['text/x-ipython-console'] |
|
230 | mimetypes = ['text/x-ipython-console'] | |
230 |
|
231 | |||
231 | # The regexps used to determine what is input and what is output. |
|
232 | # The regexps used to determine what is input and what is output. | |
232 | # The default prompts for IPython are: |
|
233 | # The default prompts for IPython are: | |
233 | # |
|
234 | # | |
234 | # c.PromptManager.in_template = 'In [\#]: ' |
|
235 | # c.PromptManager.in_template = 'In [\#]: ' | |
235 | # c.PromptManager.in2_template = ' .\D.: ' |
|
236 | # c.PromptManager.in2_template = ' .\D.: ' | |
236 | # c.PromptManager.out_template = 'Out[\#]: ' |
|
237 | # c.PromptManager.out_template = 'Out[\#]: ' | |
237 | # |
|
238 | # | |
238 | in1_regex = r'In \[[0-9]+\]: ' |
|
239 | in1_regex = r'In \[[0-9]+\]: ' | |
239 | in2_regex = r' \.\.+\.: ' |
|
240 | in2_regex = r' \.\.+\.: ' | |
240 | out_regex = r'Out\[[0-9]+\]: ' |
|
241 | out_regex = r'Out\[[0-9]+\]: ' | |
241 |
|
242 | |||
242 | #: The regex to determine when a traceback starts. |
|
243 | #: The regex to determine when a traceback starts. | |
243 | ipytb_start = re.compile(r'^(\^C)?(-+\n)|^( File)(.*)(, line )(\d+\n)') |
|
244 | ipytb_start = re.compile(r'^(\^C)?(-+\n)|^( File)(.*)(, line )(\d+\n)') | |
244 |
|
245 | |||
245 | def __init__(self, **options): |
|
246 | def __init__(self, **options): | |
246 | """Initialize the IPython console lexer. |
|
247 | """Initialize the IPython console lexer. | |
247 |
|
248 | |||
248 | Parameters |
|
249 | Parameters | |
249 | ---------- |
|
250 | ---------- | |
250 | python3 : bool |
|
251 | python3 : bool | |
251 | If `True`, then the console inputs are parsed using a Python 3 |
|
252 | If `True`, then the console inputs are parsed using a Python 3 | |
252 | lexer. Otherwise, they are parsed using a Python 2 lexer. |
|
253 | lexer. Otherwise, they are parsed using a Python 2 lexer. | |
253 | in1_regex : RegexObject |
|
254 | in1_regex : RegexObject | |
254 | The compiled regular expression used to detect the start |
|
255 | The compiled regular expression used to detect the start | |
255 | of inputs. Although the IPython configuration setting may have a |
|
256 | of inputs. Although the IPython configuration setting may have a | |
256 | trailing whitespace, do not include it in the regex. If `None`, |
|
257 | trailing whitespace, do not include it in the regex. If `None`, | |
257 | then the default input prompt is assumed. |
|
258 | then the default input prompt is assumed. | |
258 | in2_regex : RegexObject |
|
259 | in2_regex : RegexObject | |
259 | The compiled regular expression used to detect the continuation |
|
260 | The compiled regular expression used to detect the continuation | |
260 | of inputs. Although the IPython configuration setting may have a |
|
261 | of inputs. Although the IPython configuration setting may have a | |
261 | trailing whitespace, do not include it in the regex. If `None`, |
|
262 | trailing whitespace, do not include it in the regex. If `None`, | |
262 | then the default input prompt is assumed. |
|
263 | then the default input prompt is assumed. | |
263 | out_regex : RegexObject |
|
264 | out_regex : RegexObject | |
264 | The compiled regular expression used to detect outputs. If `None`, |
|
265 | The compiled regular expression used to detect outputs. If `None`, | |
265 | then the default output prompt is assumed. |
|
266 | then the default output prompt is assumed. | |
266 |
|
267 | |||
267 | """ |
|
268 | """ | |
268 | self.python3 = get_bool_opt(options, 'python3', False) |
|
269 | self.python3 = get_bool_opt(options, 'python3', False) | |
269 | if self.python3: |
|
270 | if self.python3: | |
270 | self.aliases = ['ipython3console'] |
|
271 | self.aliases = ['ipython3console'] | |
271 | else: |
|
272 | else: | |
272 | self.aliases = ['ipython2console', 'ipythonconsole'] |
|
273 | self.aliases = ['ipython2console', 'ipythonconsole'] | |
273 |
|
274 | |||
274 | in1_regex = options.get('in1_regex', self.in1_regex) |
|
275 | in1_regex = options.get('in1_regex', self.in1_regex) | |
275 | in2_regex = options.get('in2_regex', self.in2_regex) |
|
276 | in2_regex = options.get('in2_regex', self.in2_regex) | |
276 | out_regex = options.get('out_regex', self.out_regex) |
|
277 | out_regex = options.get('out_regex', self.out_regex) | |
277 |
|
278 | |||
278 | # So that we can work with input and output prompts which have been |
|
279 | # So that we can work with input and output prompts which have been | |
279 | # rstrip'd (possibly by editors) we also need rstrip'd variants. If |
|
280 | # rstrip'd (possibly by editors) we also need rstrip'd variants. If | |
280 | # we do not do this, then such prompts will be tagged as 'output'. |
|
281 | # we do not do this, then such prompts will be tagged as 'output'. | |
281 | # The reason can't just use the rstrip'd variants instead is because |
|
282 | # The reason can't just use the rstrip'd variants instead is because | |
282 | # we want any whitespace associated with the prompt to be inserted |
|
283 | # we want any whitespace associated with the prompt to be inserted | |
283 | # with the token. This allows formatted code to be modified so as hide |
|
284 | # with the token. This allows formatted code to be modified so as hide | |
284 | # the appearance of prompts, with the whitespace included. One example |
|
285 | # the appearance of prompts, with the whitespace included. One example | |
285 | # use of this is in copybutton.js from the standard lib Python docs. |
|
286 | # use of this is in copybutton.js from the standard lib Python docs. | |
286 | in1_regex_rstrip = in1_regex.rstrip() + '\n' |
|
287 | in1_regex_rstrip = in1_regex.rstrip() + '\n' | |
287 | in2_regex_rstrip = in2_regex.rstrip() + '\n' |
|
288 | in2_regex_rstrip = in2_regex.rstrip() + '\n' | |
288 | out_regex_rstrip = out_regex.rstrip() + '\n' |
|
289 | out_regex_rstrip = out_regex.rstrip() + '\n' | |
289 |
|
290 | |||
290 | # Compile and save them all. |
|
291 | # Compile and save them all. | |
291 | attrs = ['in1_regex', 'in2_regex', 'out_regex', |
|
292 | attrs = ['in1_regex', 'in2_regex', 'out_regex', | |
292 | 'in1_regex_rstrip', 'in2_regex_rstrip', 'out_regex_rstrip'] |
|
293 | 'in1_regex_rstrip', 'in2_regex_rstrip', 'out_regex_rstrip'] | |
293 | for attr in attrs: |
|
294 | for attr in attrs: | |
294 | self.__setattr__(attr, re.compile(locals()[attr])) |
|
295 | self.__setattr__(attr, re.compile(locals()[attr])) | |
295 |
|
296 | |||
296 | Lexer.__init__(self, **options) |
|
297 | Lexer.__init__(self, **options) | |
297 |
|
298 | |||
298 | if self.python3: |
|
299 | if self.python3: | |
299 | pylexer = IPython3Lexer |
|
300 | pylexer = IPython3Lexer | |
300 | tblexer = IPythonTracebackLexer |
|
301 | tblexer = IPythonTracebackLexer | |
301 | else: |
|
302 | else: | |
302 | pylexer = IPythonLexer |
|
303 | pylexer = IPythonLexer | |
303 | tblexer = IPythonTracebackLexer |
|
304 | tblexer = IPythonTracebackLexer | |
304 |
|
305 | |||
305 | self.pylexer = pylexer(**options) |
|
306 | self.pylexer = pylexer(**options) | |
306 | self.tblexer = tblexer(**options) |
|
307 | self.tblexer = tblexer(**options) | |
307 |
|
308 | |||
308 | self.reset() |
|
309 | self.reset() | |
309 |
|
310 | |||
310 | def reset(self): |
|
311 | def reset(self): | |
311 | self.mode = 'output' |
|
312 | self.mode = 'output' | |
312 | self.index = 0 |
|
313 | self.index = 0 | |
313 | self.buffer = u'' |
|
314 | self.buffer = u'' | |
314 | self.insertions = [] |
|
315 | self.insertions = [] | |
315 |
|
316 | |||
316 | def buffered_tokens(self): |
|
317 | def buffered_tokens(self): | |
317 | """ |
|
318 | """ | |
318 | Generator of unprocessed tokens after doing insertions and before |
|
319 | Generator of unprocessed tokens after doing insertions and before | |
319 | changing to a new state. |
|
320 | changing to a new state. | |
320 |
|
321 | |||
321 | """ |
|
322 | """ | |
322 | if self.mode == 'output': |
|
323 | if self.mode == 'output': | |
323 | tokens = [(0, Generic.Output, self.buffer)] |
|
324 | tokens = [(0, Generic.Output, self.buffer)] | |
324 | elif self.mode == 'input': |
|
325 | elif self.mode == 'input': | |
325 | tokens = self.pylexer.get_tokens_unprocessed(self.buffer) |
|
326 | tokens = self.pylexer.get_tokens_unprocessed(self.buffer) | |
326 | else: # traceback |
|
327 | else: # traceback | |
327 | tokens = self.tblexer.get_tokens_unprocessed(self.buffer) |
|
328 | tokens = self.tblexer.get_tokens_unprocessed(self.buffer) | |
328 |
|
329 | |||
329 | for i, t, v in do_insertions(self.insertions, tokens): |
|
330 | for i, t, v in do_insertions(self.insertions, tokens): | |
330 | # All token indexes are relative to the buffer. |
|
331 | # All token indexes are relative to the buffer. | |
331 | yield self.index + i, t, v |
|
332 | yield self.index + i, t, v | |
332 |
|
333 | |||
333 | # Clear it all |
|
334 | # Clear it all | |
334 | self.index += len(self.buffer) |
|
335 | self.index += len(self.buffer) | |
335 | self.buffer = u'' |
|
336 | self.buffer = u'' | |
336 | self.insertions = [] |
|
337 | self.insertions = [] | |
337 |
|
338 | |||
338 | def get_mci(self, line): |
|
339 | def get_mci(self, line): | |
339 | """ |
|
340 | """ | |
340 | Parses the line and returns a 3-tuple: (mode, code, insertion). |
|
341 | Parses the line and returns a 3-tuple: (mode, code, insertion). | |
341 |
|
342 | |||
342 | `mode` is the next mode (or state) of the lexer, and is always equal |
|
343 | `mode` is the next mode (or state) of the lexer, and is always equal | |
343 | to 'input', 'output', or 'tb'. |
|
344 | to 'input', 'output', or 'tb'. | |
344 |
|
345 | |||
345 | `code` is a portion of the line that should be added to the buffer |
|
346 | `code` is a portion of the line that should be added to the buffer | |
346 | corresponding to the next mode and eventually lexed by another lexer. |
|
347 | corresponding to the next mode and eventually lexed by another lexer. | |
347 | For example, `code` could be Python code if `mode` were 'input'. |
|
348 | For example, `code` could be Python code if `mode` were 'input'. | |
348 |
|
349 | |||
349 | `insertion` is a 3-tuple (index, token, text) representing an |
|
350 | `insertion` is a 3-tuple (index, token, text) representing an | |
350 | unprocessed "token" that will be inserted into the stream of tokens |
|
351 | unprocessed "token" that will be inserted into the stream of tokens | |
351 | that are created from the buffer once we change modes. This is usually |
|
352 | that are created from the buffer once we change modes. This is usually | |
352 | the input or output prompt. |
|
353 | the input or output prompt. | |
353 |
|
354 | |||
354 | In general, the next mode depends on current mode and on the contents |
|
355 | In general, the next mode depends on current mode and on the contents | |
355 | of `line`. |
|
356 | of `line`. | |
356 |
|
357 | |||
357 | """ |
|
358 | """ | |
358 | # To reduce the number of regex match checks, we have multiple |
|
359 | # To reduce the number of regex match checks, we have multiple | |
359 | # 'if' blocks instead of 'if-elif' blocks. |
|
360 | # 'if' blocks instead of 'if-elif' blocks. | |
360 |
|
361 | |||
361 | # Check for possible end of input |
|
362 | # Check for possible end of input | |
362 | in2_match = self.in2_regex.match(line) |
|
363 | in2_match = self.in2_regex.match(line) | |
363 | in2_match_rstrip = self.in2_regex_rstrip.match(line) |
|
364 | in2_match_rstrip = self.in2_regex_rstrip.match(line) | |
364 | if (in2_match and in2_match.group().rstrip() == line.rstrip()) or \ |
|
365 | if (in2_match and in2_match.group().rstrip() == line.rstrip()) or \ | |
365 | in2_match_rstrip: |
|
366 | in2_match_rstrip: | |
366 | end_input = True |
|
367 | end_input = True | |
367 | else: |
|
368 | else: | |
368 | end_input = False |
|
369 | end_input = False | |
369 | if end_input and self.mode != 'tb': |
|
370 | if end_input and self.mode != 'tb': | |
370 | # Only look for an end of input when not in tb mode. |
|
371 | # Only look for an end of input when not in tb mode. | |
371 | # An ellipsis could appear within the traceback. |
|
372 | # An ellipsis could appear within the traceback. | |
372 | mode = 'output' |
|
373 | mode = 'output' | |
373 | code = u'' |
|
374 | code = u'' | |
374 | insertion = (0, Generic.Prompt, line) |
|
375 | insertion = (0, Generic.Prompt, line) | |
375 | return mode, code, insertion |
|
376 | return mode, code, insertion | |
376 |
|
377 | |||
377 | # Check for output prompt |
|
378 | # Check for output prompt | |
378 | out_match = self.out_regex.match(line) |
|
379 | out_match = self.out_regex.match(line) | |
379 | out_match_rstrip = self.out_regex_rstrip.match(line) |
|
380 | out_match_rstrip = self.out_regex_rstrip.match(line) | |
380 | if out_match or out_match_rstrip: |
|
381 | if out_match or out_match_rstrip: | |
381 | mode = 'output' |
|
382 | mode = 'output' | |
382 | if out_match: |
|
383 | if out_match: | |
383 | idx = out_match.end() |
|
384 | idx = out_match.end() | |
384 | else: |
|
385 | else: | |
385 | idx = out_match_rstrip.end() |
|
386 | idx = out_match_rstrip.end() | |
386 | code = line[idx:] |
|
387 | code = line[idx:] | |
387 | # Use the 'heading' token for output. We cannot use Generic.Error |
|
388 | # Use the 'heading' token for output. We cannot use Generic.Error | |
388 | # since it would conflict with exceptions. |
|
389 | # since it would conflict with exceptions. | |
389 | insertion = (0, Generic.Heading, line[:idx]) |
|
390 | insertion = (0, Generic.Heading, line[:idx]) | |
390 | return mode, code, insertion |
|
391 | return mode, code, insertion | |
391 |
|
392 | |||
392 |
|
393 | |||
393 | # Check for input or continuation prompt (non stripped version) |
|
394 | # Check for input or continuation prompt (non stripped version) | |
394 | in1_match = self.in1_regex.match(line) |
|
395 | in1_match = self.in1_regex.match(line) | |
395 | if in1_match or (in2_match and self.mode != 'tb'): |
|
396 | if in1_match or (in2_match and self.mode != 'tb'): | |
396 | # New input or when not in tb, continued input. |
|
397 | # New input or when not in tb, continued input. | |
397 | # We do not check for continued input when in tb since it is |
|
398 | # We do not check for continued input when in tb since it is | |
398 | # allowable to replace a long stack with an ellipsis. |
|
399 | # allowable to replace a long stack with an ellipsis. | |
399 | mode = 'input' |
|
400 | mode = 'input' | |
400 | if in1_match: |
|
401 | if in1_match: | |
401 | idx = in1_match.end() |
|
402 | idx = in1_match.end() | |
402 | else: # in2_match |
|
403 | else: # in2_match | |
403 | idx = in2_match.end() |
|
404 | idx = in2_match.end() | |
404 | code = line[idx:] |
|
405 | code = line[idx:] | |
405 | insertion = (0, Generic.Prompt, line[:idx]) |
|
406 | insertion = (0, Generic.Prompt, line[:idx]) | |
406 | return mode, code, insertion |
|
407 | return mode, code, insertion | |
407 |
|
408 | |||
408 | # Check for input or continuation prompt (stripped version) |
|
409 | # Check for input or continuation prompt (stripped version) | |
409 | in1_match_rstrip = self.in1_regex_rstrip.match(line) |
|
410 | in1_match_rstrip = self.in1_regex_rstrip.match(line) | |
410 | if in1_match_rstrip or (in2_match_rstrip and self.mode != 'tb'): |
|
411 | if in1_match_rstrip or (in2_match_rstrip and self.mode != 'tb'): | |
411 | # New input or when not in tb, continued input. |
|
412 | # New input or when not in tb, continued input. | |
412 | # We do not check for continued input when in tb since it is |
|
413 | # We do not check for continued input when in tb since it is | |
413 | # allowable to replace a long stack with an ellipsis. |
|
414 | # allowable to replace a long stack with an ellipsis. | |
414 | mode = 'input' |
|
415 | mode = 'input' | |
415 | if in1_match_rstrip: |
|
416 | if in1_match_rstrip: | |
416 | idx = in1_match_rstrip.end() |
|
417 | idx = in1_match_rstrip.end() | |
417 | else: # in2_match |
|
418 | else: # in2_match | |
418 | idx = in2_match_rstrip.end() |
|
419 | idx = in2_match_rstrip.end() | |
419 | code = line[idx:] |
|
420 | code = line[idx:] | |
420 | insertion = (0, Generic.Prompt, line[:idx]) |
|
421 | insertion = (0, Generic.Prompt, line[:idx]) | |
421 | return mode, code, insertion |
|
422 | return mode, code, insertion | |
422 |
|
423 | |||
423 | # Check for traceback |
|
424 | # Check for traceback | |
424 | if self.ipytb_start.match(line): |
|
425 | if self.ipytb_start.match(line): | |
425 | mode = 'tb' |
|
426 | mode = 'tb' | |
426 | code = line |
|
427 | code = line | |
427 | insertion = None |
|
428 | insertion = None | |
428 | return mode, code, insertion |
|
429 | return mode, code, insertion | |
429 |
|
430 | |||
430 | # All other stuff... |
|
431 | # All other stuff... | |
431 | if self.mode in ('input', 'output'): |
|
432 | if self.mode in ('input', 'output'): | |
432 | # We assume all other text is output. Multiline input that |
|
433 | # We assume all other text is output. Multiline input that | |
433 | # does not use the continuation marker cannot be detected. |
|
434 | # does not use the continuation marker cannot be detected. | |
434 | # For example, the 3 in the following is clearly output: |
|
435 | # For example, the 3 in the following is clearly output: | |
435 | # |
|
436 | # | |
436 | # In [1]: print 3 |
|
437 | # In [1]: print 3 | |
437 | # 3 |
|
438 | # 3 | |
438 | # |
|
439 | # | |
439 | # But the following second line is part of the input: |
|
440 | # But the following second line is part of the input: | |
440 | # |
|
441 | # | |
441 | # In [2]: while True: |
|
442 | # In [2]: while True: | |
442 | # print True |
|
443 | # print True | |
443 | # |
|
444 | # | |
444 | # In both cases, the 2nd line will be 'output'. |
|
445 | # In both cases, the 2nd line will be 'output'. | |
445 | # |
|
446 | # | |
446 | mode = 'output' |
|
447 | mode = 'output' | |
447 | else: |
|
448 | else: | |
448 | mode = 'tb' |
|
449 | mode = 'tb' | |
449 |
|
450 | |||
450 | code = line |
|
451 | code = line | |
451 | insertion = None |
|
452 | insertion = None | |
452 |
|
453 | |||
453 | return mode, code, insertion |
|
454 | return mode, code, insertion | |
454 |
|
455 | |||
455 | def get_tokens_unprocessed(self, text): |
|
456 | def get_tokens_unprocessed(self, text): | |
456 | self.reset() |
|
457 | self.reset() | |
457 | for match in line_re.finditer(text): |
|
458 | for match in line_re.finditer(text): | |
458 | line = match.group() |
|
459 | line = match.group() | |
459 | mode, code, insertion = self.get_mci(line) |
|
460 | mode, code, insertion = self.get_mci(line) | |
460 |
|
461 | |||
461 | if mode != self.mode: |
|
462 | if mode != self.mode: | |
462 | # Yield buffered tokens before transitioning to new mode. |
|
463 | # Yield buffered tokens before transitioning to new mode. | |
463 | for token in self.buffered_tokens(): |
|
464 | for token in self.buffered_tokens(): | |
464 | yield token |
|
465 | yield token | |
465 | self.mode = mode |
|
466 | self.mode = mode | |
466 |
|
467 | |||
467 | if insertion: |
|
468 | if insertion: | |
468 | self.insertions.append((len(self.buffer), [insertion])) |
|
469 | self.insertions.append((len(self.buffer), [insertion])) | |
469 | self.buffer += code |
|
470 | self.buffer += code | |
470 | else: |
|
471 | else: | |
471 | for token in self.buffered_tokens(): |
|
472 | for token in self.buffered_tokens(): | |
472 | yield token |
|
473 | yield token | |
473 |
|
474 | |||
474 | class IPyLexer(Lexer): |
|
475 | class IPyLexer(Lexer): | |
475 | """ |
|
476 | """ | |
476 | Primary lexer for all IPython-like code. |
|
477 | Primary lexer for all IPython-like code. | |
477 |
|
478 | |||
478 | This is a simple helper lexer. If the first line of the text begins with |
|
479 | This is a simple helper lexer. If the first line of the text begins with | |
479 | "In \[[0-9]+\]:", then the entire text is parsed with an IPython console |
|
480 | "In \[[0-9]+\]:", then the entire text is parsed with an IPython console | |
480 | lexer. If not, then the entire text is parsed with an IPython lexer. |
|
481 | lexer. If not, then the entire text is parsed with an IPython lexer. | |
481 |
|
482 | |||
482 | The goal is to reduce the number of lexers that are registered |
|
483 | The goal is to reduce the number of lexers that are registered | |
483 | with Pygments. |
|
484 | with Pygments. | |
484 |
|
485 | |||
485 | """ |
|
486 | """ | |
486 | name = 'IPy session' |
|
487 | name = 'IPy session' | |
487 | aliases = ['ipy'] |
|
488 | aliases = ['ipy'] | |
488 |
|
489 | |||
489 | def __init__(self, **options): |
|
490 | def __init__(self, **options): | |
490 | self.python3 = get_bool_opt(options, 'python3', False) |
|
491 | self.python3 = get_bool_opt(options, 'python3', False) | |
491 | if self.python3: |
|
492 | if self.python3: | |
492 | self.aliases = ['ipy3'] |
|
493 | self.aliases = ['ipy3'] | |
493 | else: |
|
494 | else: | |
494 | self.aliases = ['ipy2', 'ipy'] |
|
495 | self.aliases = ['ipy2', 'ipy'] | |
495 |
|
496 | |||
496 | Lexer.__init__(self, **options) |
|
497 | Lexer.__init__(self, **options) | |
497 |
|
498 | |||
498 | self.IPythonLexer = IPythonLexer(**options) |
|
499 | self.IPythonLexer = IPythonLexer(**options) | |
499 | self.IPythonConsoleLexer = IPythonConsoleLexer(**options) |
|
500 | self.IPythonConsoleLexer = IPythonConsoleLexer(**options) | |
500 |
|
501 | |||
501 | def get_tokens_unprocessed(self, text): |
|
502 | def get_tokens_unprocessed(self, text): | |
502 | # Search for the input prompt anywhere...this allows code blocks to |
|
503 | # Search for the input prompt anywhere...this allows code blocks to | |
503 | # begin with comments as well. |
|
504 | # begin with comments as well. | |
504 | if re.match(r'.*(In \[[0-9]+\]:)', text.strip(), re.DOTALL): |
|
505 | if re.match(r'.*(In \[[0-9]+\]:)', text.strip(), re.DOTALL): | |
505 | lex = self.IPythonConsoleLexer |
|
506 | lex = self.IPythonConsoleLexer | |
506 | else: |
|
507 | else: | |
507 | lex = self.IPythonLexer |
|
508 | lex = self.IPythonLexer | |
508 | for token in lex.get_tokens_unprocessed(text): |
|
509 | for token in lex.get_tokens_unprocessed(text): | |
509 | yield token |
|
510 | yield token | |
510 |
|
511 |
@@ -1,122 +1,130 b'' | |||||
1 | """Test lexers module""" |
|
1 | """Test lexers module""" | |
2 |
|
2 | |||
3 | # Copyright (c) IPython Development Team. |
|
3 | # Copyright (c) IPython Development Team. | |
4 | # Distributed under the terms of the Modified BSD License. |
|
4 | # Distributed under the terms of the Modified BSD License. | |
5 |
|
5 | |||
6 | from unittest import TestCase |
|
6 | from unittest import TestCase | |
7 | from pygments.token import Token |
|
7 | from pygments.token import Token | |
8 |
|
8 | |||
9 | from .. import lexers |
|
9 | from .. import lexers | |
10 |
|
10 | |||
11 |
|
11 | |||
12 | class TestLexers(TestCase): |
|
12 | class TestLexers(TestCase): | |
13 | """Collection of lexers tests""" |
|
13 | """Collection of lexers tests""" | |
14 | def setUp(self): |
|
14 | def setUp(self): | |
15 | self.lexer = lexers.IPythonLexer() |
|
15 | self.lexer = lexers.IPythonLexer() | |
16 |
|
16 | |||
17 | def testIPythonLexer(self): |
|
17 | def testIPythonLexer(self): | |
18 | fragment = '!echo $HOME\n' |
|
18 | fragment = '!echo $HOME\n' | |
19 | tokens = [ |
|
19 | tokens = [ | |
20 | (Token.Operator, '!'), |
|
20 | (Token.Operator, '!'), | |
21 | (Token.Name.Builtin, 'echo'), |
|
21 | (Token.Name.Builtin, 'echo'), | |
22 | (Token.Text, ' '), |
|
22 | (Token.Text, ' '), | |
23 | (Token.Name.Variable, '$HOME'), |
|
23 | (Token.Name.Variable, '$HOME'), | |
24 | (Token.Text, '\n'), |
|
24 | (Token.Text, '\n'), | |
25 | ] |
|
25 | ] | |
26 | self.assertEqual(tokens, list(self.lexer.get_tokens(fragment))) |
|
26 | self.assertEqual(tokens, list(self.lexer.get_tokens(fragment))) | |
27 |
|
27 | |||
28 | fragment_2 = '!' + fragment |
|
28 | fragment_2 = '!' + fragment | |
29 | tokens_2 = [ |
|
29 | tokens_2 = [ | |
30 | (Token.Operator, '!!'), |
|
30 | (Token.Operator, '!!'), | |
31 | ] + tokens[1:] |
|
31 | ] + tokens[1:] | |
32 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) |
|
32 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) | |
33 |
|
33 | |||
34 | fragment_2 = '\t %%!\n' + fragment[1:] |
|
34 | fragment_2 = '\t %%!\n' + fragment[1:] | |
35 | tokens_2 = [ |
|
35 | tokens_2 = [ | |
36 | (Token.Text, '\t '), |
|
36 | (Token.Text, '\t '), | |
37 | (Token.Operator, '%%!'), |
|
37 | (Token.Operator, '%%!'), | |
38 | (Token.Text, '\n'), |
|
38 | (Token.Text, '\n'), | |
39 | ] + tokens[1:] |
|
39 | ] + tokens[1:] | |
40 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) |
|
40 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) | |
41 |
|
41 | |||
42 | fragment_2 = 'x = ' + fragment |
|
42 | fragment_2 = 'x = ' + fragment | |
43 | tokens_2 = [ |
|
43 | tokens_2 = [ | |
44 | (Token.Name, 'x'), |
|
44 | (Token.Name, 'x'), | |
45 | (Token.Text, ' '), |
|
45 | (Token.Text, ' '), | |
46 | (Token.Operator, '='), |
|
46 | (Token.Operator, '='), | |
47 | (Token.Text, ' '), |
|
47 | (Token.Text, ' '), | |
48 | ] + tokens |
|
48 | ] + tokens | |
49 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) |
|
49 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) | |
50 |
|
50 | |||
51 | fragment_2 = 'x, = ' + fragment |
|
51 | fragment_2 = 'x, = ' + fragment | |
52 | tokens_2 = [ |
|
52 | tokens_2 = [ | |
53 | (Token.Name, 'x'), |
|
53 | (Token.Name, 'x'), | |
54 | (Token.Punctuation, ','), |
|
54 | (Token.Punctuation, ','), | |
55 | (Token.Text, ' '), |
|
55 | (Token.Text, ' '), | |
56 | (Token.Operator, '='), |
|
56 | (Token.Operator, '='), | |
57 | (Token.Text, ' '), |
|
57 | (Token.Text, ' '), | |
58 | ] + tokens |
|
58 | ] + tokens | |
59 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) |
|
59 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) | |
60 |
|
60 | |||
61 | fragment_2 = 'x, = %sx ' + fragment[1:] |
|
61 | fragment_2 = 'x, = %sx ' + fragment[1:] | |
62 | tokens_2 = [ |
|
62 | tokens_2 = [ | |
63 | (Token.Name, 'x'), |
|
63 | (Token.Name, 'x'), | |
64 | (Token.Punctuation, ','), |
|
64 | (Token.Punctuation, ','), | |
65 | (Token.Text, ' '), |
|
65 | (Token.Text, ' '), | |
66 | (Token.Operator, '='), |
|
66 | (Token.Operator, '='), | |
67 | (Token.Text, ' '), |
|
67 | (Token.Text, ' '), | |
68 | (Token.Operator, '%'), |
|
68 | (Token.Operator, '%'), | |
69 | (Token.Keyword, 'sx'), |
|
69 | (Token.Keyword, 'sx'), | |
70 | (Token.Text, ' '), |
|
70 | (Token.Text, ' '), | |
71 | ] + tokens[1:] |
|
71 | ] + tokens[1:] | |
72 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) |
|
72 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) | |
73 |
|
73 | |||
74 | fragment_2 = 'f = %R function () {}\n' |
|
74 | fragment_2 = 'f = %R function () {}\n' | |
75 | tokens_2 = [ |
|
75 | tokens_2 = [ | |
76 | (Token.Name, 'f'), |
|
76 | (Token.Name, 'f'), | |
77 | (Token.Text, ' '), |
|
77 | (Token.Text, ' '), | |
78 | (Token.Operator, '='), |
|
78 | (Token.Operator, '='), | |
79 | (Token.Text, ' '), |
|
79 | (Token.Text, ' '), | |
80 | (Token.Operator, '%'), |
|
80 | (Token.Operator, '%'), | |
81 | (Token.Keyword, 'R'), |
|
81 | (Token.Keyword, 'R'), | |
82 | (Token.Text, ' function () {}\n'), |
|
82 | (Token.Text, ' function () {}\n'), | |
83 | ] |
|
83 | ] | |
84 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) |
|
84 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) | |
85 |
|
85 | |||
86 | fragment_2 = '\t%%xyz\n$foo\n' |
|
86 | fragment_2 = '\t%%xyz\n$foo\n' | |
87 | tokens_2 = [ |
|
87 | tokens_2 = [ | |
88 | (Token.Text, '\t'), |
|
88 | (Token.Text, '\t'), | |
89 | (Token.Operator, '%%'), |
|
89 | (Token.Operator, '%%'), | |
90 | (Token.Keyword, 'xyz'), |
|
90 | (Token.Keyword, 'xyz'), | |
91 | (Token.Text, '\n$foo\n'), |
|
91 | (Token.Text, '\n$foo\n'), | |
92 | ] |
|
92 | ] | |
93 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) |
|
93 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) | |
94 |
|
94 | |||
95 | fragment_2 = '%system?\n' |
|
95 | fragment_2 = '%system?\n' | |
96 | tokens_2 = [ |
|
96 | tokens_2 = [ | |
97 | (Token.Operator, '%'), |
|
97 | (Token.Operator, '%'), | |
98 | (Token.Keyword, 'system'), |
|
98 | (Token.Keyword, 'system'), | |
99 | (Token.Operator, '?'), |
|
99 | (Token.Operator, '?'), | |
100 | (Token.Text, '\n'), |
|
100 | (Token.Text, '\n'), | |
101 | ] |
|
101 | ] | |
102 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) |
|
102 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) | |
103 |
|
103 | |||
104 | fragment_2 = 'x != y\n' |
|
104 | fragment_2 = 'x != y\n' | |
105 | tokens_2 = [ |
|
105 | tokens_2 = [ | |
106 | (Token.Name, 'x'), |
|
106 | (Token.Name, 'x'), | |
107 | (Token.Text, ' '), |
|
107 | (Token.Text, ' '), | |
108 | (Token.Operator, '!='), |
|
108 | (Token.Operator, '!='), | |
109 | (Token.Text, ' '), |
|
109 | (Token.Text, ' '), | |
110 | (Token.Name, 'y'), |
|
110 | (Token.Name, 'y'), | |
111 | (Token.Text, '\n'), |
|
111 | (Token.Text, '\n'), | |
112 | ] |
|
112 | ] | |
113 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) |
|
113 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) | |
114 |
|
114 | |||
115 | fragment_2 = ' ?math.sin\n' |
|
115 | fragment_2 = ' ?math.sin\n' | |
116 | tokens_2 = [ |
|
116 | tokens_2 = [ | |
117 | (Token.Text, ' '), |
|
117 | (Token.Text, ' '), | |
118 | (Token.Operator, '?'), |
|
118 | (Token.Operator, '?'), | |
119 | (Token.Text, 'math.sin'), |
|
119 | (Token.Text, 'math.sin'), | |
120 | (Token.Text, '\n'), |
|
120 | (Token.Text, '\n'), | |
121 | ] |
|
121 | ] | |
122 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) |
|
122 | self.assertEqual(tokens_2, list(self.lexer.get_tokens(fragment_2))) | |
|
123 | ||||
|
124 | fragment = ' *int*?\n' | |||
|
125 | tokens = [ | |||
|
126 | (Token.Text, ' *int*'), | |||
|
127 | (Token.Operator, '?'), | |||
|
128 | (Token.Text, '\n'), | |||
|
129 | ] | |||
|
130 | self.assertEqual(tokens, list(self.lexer.get_tokens(fragment))) |
General Comments 0
You need to be logged in to leave comments.
Login now