STRling 2.0.0__tar.gz → 2.1.0__tar.gz
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.
- {strling-2.0.0 → strling-2.1.0}/PKG-INFO +75 -39
- {strling-2.0.0 → strling-2.1.0}/README.md +74 -38
- strling-2.1.0/STRling/simply/constructors.py +211 -0
- strling-2.1.0/STRling/simply/lookarounds.py +105 -0
- strling-2.1.0/STRling/simply/pattern.py +271 -0
- strling-2.1.0/STRling/simply/sets.py +265 -0
- {strling-2.0.0 → strling-2.1.0}/STRling/simply/static.py +43 -23
- {strling-2.0.0 → strling-2.1.0}/STRling.egg-info/PKG-INFO +75 -39
- {strling-2.0.0 → strling-2.1.0}/setup.py +1 -1
- strling-2.0.0/STRling/simply/constructors.py +0 -156
- strling-2.0.0/STRling/simply/lookarounds.py +0 -124
- strling-2.0.0/STRling/simply/pattern.py +0 -160
- strling-2.0.0/STRling/simply/sets.py +0 -225
- {strling-2.0.0 → strling-2.1.0}/STRling/__init__.py +0 -0
- {strling-2.0.0 → strling-2.1.0}/STRling/simply/__init__.py +0 -0
- {strling-2.0.0 → strling-2.1.0}/STRling/templates/__init__.py +0 -0
- {strling-2.0.0 → strling-2.1.0}/STRling/templates/templates.py +0 -0
- {strling-2.0.0 → strling-2.1.0}/STRling/templates_v1.py +0 -0
- {strling-2.0.0 → strling-2.1.0}/STRling.egg-info/SOURCES.txt +0 -0
- {strling-2.0.0 → strling-2.1.0}/STRling.egg-info/dependency_links.txt +0 -0
- {strling-2.0.0 → strling-2.1.0}/STRling.egg-info/top_level.txt +0 -0
- {strling-2.0.0 → strling-2.1.0}/setup.cfg +0 -0
|
@@ -1,13 +1,13 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: STRling
|
|
3
|
-
Version: 2.
|
|
3
|
+
Version: 2.1.0
|
|
4
4
|
Description-Content-Type: text/markdown
|
|
5
5
|
|
|
6
6
|
# STRling
|
|
7
7
|
|
|
8
8
|
## The Next Generation of Regular Expressions
|
|
9
9
|
|
|
10
|
-
STRling is a next-generation production-grade syntax designed as a user interface for writing powerful regular expressions (RegEx) with an object-oriented approach and instructional error handling. STRling recognizes the cryptic nature of raw regular expression can be challenging and susceptibility to errors, which is why STRling looks and feels nothing like RegEx while maintaining the same power and flexibility. String validation should be simple and enjoyable, not a hassle. Best of all, STRling syntax is built upon the RegEx engine, making it fully compatible with all libraries that accept RegEx along with the traditional RegEx methods built
|
|
10
|
+
STRling is a next-generation production-grade syntax designed as a user interface for writing powerful regular expressions (RegEx) with an object-oriented approach and instructional error handling. STRling recognizes the cryptic nature of raw regular expression can be challenging and susceptibility to errors, which is why STRling looks and feels nothing like RegEx while maintaining the same power and flexibility. String validation should be simple and enjoyable, not a hassle. Best of all, STRling syntax is built upon the RegEx engine, making it fully compatible with all libraries that accept RegEx along with the traditional RegEx methods built-in to Python.
|
|
11
11
|
|
|
12
12
|
### Why STRling?
|
|
13
13
|
|
|
@@ -45,20 +45,20 @@ import re
|
|
|
45
45
|
# - 1234567890
|
|
46
46
|
|
|
47
47
|
# Separator: either space or hyphen
|
|
48
|
-
separator = s.in_(
|
|
48
|
+
separator = s.in_(' -')
|
|
49
49
|
|
|
50
50
|
# Optional area code part: 123 even if in parenthesis like (123)
|
|
51
51
|
area_code = s.merge( # notice we use merge since we don't want to name the group with parenthesis
|
|
52
|
-
s.may(
|
|
52
|
+
s.may('('), # Optional opening parenthesis
|
|
53
53
|
s.group('area_code', s.digit(3)), # Exactly 3 digits and named for later reference
|
|
54
|
-
s.may(
|
|
54
|
+
s.may(')') # Optional closing parenthesis
|
|
55
55
|
)
|
|
56
56
|
|
|
57
57
|
# Central part: 456
|
|
58
|
-
central_part = s.group('central_part', s.digit(3))
|
|
58
|
+
central_part = s.group('central_part', s.digit(3)) # Exactly 3 digits and named for later reference
|
|
59
59
|
|
|
60
60
|
# Last part: 7890
|
|
61
|
-
last_part = s.group("last_part", s.digit(4))
|
|
61
|
+
last_part = s.group("last_part", s.digit(4)) # Exactly 4 digits and named for later reference
|
|
62
62
|
|
|
63
63
|
# Combine all parts into the final phone number pattern
|
|
64
64
|
# Notice we don't name the whole pattern since we can already reference it
|
|
@@ -73,7 +73,7 @@ phone_number_pattern = s.merge(
|
|
|
73
73
|
# Example usage
|
|
74
74
|
# Note: To make a pattern a RegEx string compatible with other engines use `str(pattern)`.
|
|
75
75
|
example_text = "(123) 456-7890 and 123-456-7890"
|
|
76
|
-
pattern = re.compile(str(phone_number_pattern))
|
|
76
|
+
pattern = re.compile(str(phone_number_pattern)) # Notice str(pattern)
|
|
77
77
|
matches = pattern.finditer(example_text)
|
|
78
78
|
|
|
79
79
|
for match in matches:
|
|
@@ -113,13 +113,13 @@ import re
|
|
|
113
113
|
# For example, simply.letter(1, 3) will match 1 to 3 letters.
|
|
114
114
|
|
|
115
115
|
# But some methods take an unknown number of parameters and can't distinguish the range.
|
|
116
|
-
# For example, s.merge(simply.letter(), simply.digit(), 1, 2). <====
|
|
116
|
+
# For example, s.merge(simply.letter(), simply.digit(), 1, 2). <==== INVALID
|
|
117
117
|
|
|
118
|
-
# However, all methods allow setting the range by
|
|
118
|
+
# However, all methods allow setting the range by externally invoking unless otherwise specified.
|
|
119
119
|
# For example, simply.letter()(1, 2) is the same as simply.letter(1, 2).
|
|
120
120
|
|
|
121
121
|
# This external invocation may seem useless, but it can solve our earlier issue.
|
|
122
|
-
# For example, s.merge(simply.letter(), simply.digit())(1, 2). <====
|
|
122
|
+
# For example, s.merge(simply.letter(), simply.digit())(1, 2). <==== VALID
|
|
123
123
|
|
|
124
124
|
# Notice for all functions (where repetition is valid) we can invoke the range outside the parameters,
|
|
125
125
|
# but it is primarily useful for functions with an unknown number of parameters.
|
|
@@ -148,6 +148,18 @@ s.tab() # Matches a tab character.
|
|
|
148
148
|
s.carriage() # Matches a carriage return character.
|
|
149
149
|
s.bound() # Matches a boundary character.
|
|
150
150
|
|
|
151
|
+
####################
|
|
152
|
+
# Anchors
|
|
153
|
+
####################
|
|
154
|
+
|
|
155
|
+
s.start() # Matches the start of a line.
|
|
156
|
+
# There is no `simply.not_start()` function.
|
|
157
|
+
# Instead, use `simply.not_behind(simply.start())`.
|
|
158
|
+
|
|
159
|
+
s.end() # Matches the end of a line.
|
|
160
|
+
# There is no `simply.not_end()` function.
|
|
161
|
+
# Instead, use `simply.not_ahead(simply.end())`.
|
|
162
|
+
|
|
151
163
|
####################
|
|
152
164
|
# Custom Sets
|
|
153
165
|
####################
|
|
@@ -160,43 +172,26 @@ s.between(0, 9) # Matches any digit from 0 to 9.
|
|
|
160
172
|
s.between('a', 'z') # Matches any lowercase letter from 'a' to 'z'.
|
|
161
173
|
s.between('A', 'Z') # Matches any uppercase letter from 'A' to 'Z'.
|
|
162
174
|
|
|
163
|
-
# Matches any
|
|
164
|
-
s.in_(s.letter(), s.digit(),
|
|
165
|
-
#
|
|
166
|
-
# Key distinctions:
|
|
167
|
-
# - simply.in_() typically processes faster than simply.any_of().
|
|
168
|
-
# - simply.any_of() can process composite patterns while simply.in_() cannot.
|
|
169
|
-
# A composite pattern is one consisting of smaller combined patterns.
|
|
170
|
-
|
|
171
|
-
####################
|
|
172
|
-
# Anchors
|
|
173
|
-
####################
|
|
174
|
-
|
|
175
|
-
s.start() # Matches the start of a line.
|
|
176
|
-
# There is no `simply.not_start()` function.
|
|
177
|
-
# Instead, use `simply.not_behind(simply.start())`.
|
|
178
|
-
|
|
179
|
-
s.end() # Matches the end of a line.
|
|
180
|
-
# There is no `simply.not_end()` function.
|
|
181
|
-
# Instead, use `simply.not_ahead(simply.end())`.
|
|
175
|
+
# Matches any provided patterns, but they can't include subpatterns.
|
|
176
|
+
s.in_(s.letter(), s.digit(), ',.') # Matches any letter, digit, comma, and period.
|
|
177
|
+
# A composite pattern is one consisting of subpatterns (created by constructors and lookarounds).
|
|
182
178
|
|
|
183
179
|
####################
|
|
184
180
|
# Constructors
|
|
185
181
|
####################
|
|
186
182
|
|
|
187
|
-
s.any_of() # Matches any
|
|
188
|
-
#
|
|
189
|
-
#
|
|
190
|
-
|
|
191
|
-
|
|
192
|
-
# A composite pattern is one consisting of smaller combined patterns.
|
|
193
|
-
s.any_of(pattern1, pattern2) # Matches only if one of the patterns listed is present.
|
|
183
|
+
s.any_of() # Matches any pattern, including patterns consisting of subpatterns.
|
|
184
|
+
# A composite pattern is one consisting of subpatterns (created by constructors and lookarounds).
|
|
185
|
+
pattern1 = s.merge(s.digit(3), s.letter(3)) # Matches 3 digits followed by 3 letters.
|
|
186
|
+
pattern2 = s.merge(s.letter(3), s.digit(3)) # Matches 3 letters followed by 3 digits.
|
|
187
|
+
s.any_of(pattern1, pattern2) # Matches either pattern1 or pattern2
|
|
194
188
|
|
|
195
189
|
|
|
196
190
|
s.may() # Optionally matches the provided patterns.
|
|
197
191
|
# If a `may` pattern isn't there, it still will match the rest of the patterns.
|
|
198
|
-
# In the text, "ABC2" the patter below matches ['A', 'B', 'C2']
|
|
199
192
|
s.merge(s.letter(), s.may(s.digit()))
|
|
193
|
+
# Matches any letter, and includes any digit following the letter.
|
|
194
|
+
# In the text, "AB2" the pattern above matches 'A' and 'B2'.
|
|
200
195
|
|
|
201
196
|
|
|
202
197
|
s.merge() # Combines multiple patterns into one larger pattern.
|
|
@@ -207,12 +202,53 @@ s.capture() # Creates a numbered group that can be indexed for extracting part
|
|
|
207
202
|
# Capture is used the same as merge.
|
|
208
203
|
s.capture(s.letter(), s.digit())
|
|
209
204
|
|
|
205
|
+
# Captures CANNOT be invoked with a range: s.capture(s.digit(), s.letter())(1, 2) <== INVALID
|
|
206
|
+
# Captures CAN be invoked with a number of copies: s.capture(s.digit(), s.letter())(3) <== VALID
|
|
207
|
+
|
|
208
|
+
three_digit_group = s.capture(s.digit(3))
|
|
209
|
+
four_groups_of_three = three_digit_groups(4)
|
|
210
|
+
|
|
211
|
+
example_text = "Here is a number: 111222333444"
|
|
212
|
+
match = re.search(str(four_groups_of_three), example_text) # Notice str(pattern)
|
|
213
|
+
|
|
214
|
+
print("Full Match:", match.group())
|
|
215
|
+
print("First:", match.group(1))
|
|
216
|
+
print("Second:", match.group(2))
|
|
217
|
+
print("Third:", match.group(3))
|
|
218
|
+
print("Fourth:", match.group(4))
|
|
219
|
+
|
|
220
|
+
# Output:
|
|
221
|
+
# Full Match: 111222333444
|
|
222
|
+
# First: 111
|
|
223
|
+
# Second: 222
|
|
224
|
+
# Third: 333
|
|
225
|
+
# Fourth: 444
|
|
226
|
+
|
|
210
227
|
|
|
211
228
|
s.group() # Creates a named group that can be referenced for extracting part of a match.
|
|
212
229
|
# group is used the same as merge and capture but it takes a string name as the first argument.
|
|
213
230
|
s.group('my_group', s.letter(), s.digit())
|
|
214
|
-
|
|
231
|
+
|
|
232
|
+
# Unlike merge and capture, groups CANNOT be invoked with a range.
|
|
215
233
|
# This is because group names must be unique in a pattern.
|
|
234
|
+
# s.group('unique_name', s.digit())(1, 2) <== INVALID
|
|
235
|
+
|
|
236
|
+
# Groups can easily be referenced from the match by name
|
|
237
|
+
# assuming the numbers have been grouped and named properly.
|
|
238
|
+
example_text = "Here is a phone number: 123-456-7890."
|
|
239
|
+
match = re.search(str(phone_number_pattern), example_text) # Notice str(pattern)
|
|
240
|
+
|
|
241
|
+
print("Full Match:", match.group())
|
|
242
|
+
print("Area Code:", match.group("area_code"))
|
|
243
|
+
print("Central Part:", match.group("central_part"))
|
|
244
|
+
print("Last Part:", match.group("last_part"))
|
|
245
|
+
|
|
246
|
+
# Output:
|
|
247
|
+
# Full Match: 123-456-7890
|
|
248
|
+
# Area Code: 123
|
|
249
|
+
# Central Part: 456
|
|
250
|
+
# Last Part: 7890
|
|
251
|
+
|
|
216
252
|
|
|
217
253
|
####################
|
|
218
254
|
# Lookarounds
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
## The Next Generation of Regular Expressions
|
|
4
4
|
|
|
5
|
-
STRling is a next-generation production-grade syntax designed as a user interface for writing powerful regular expressions (RegEx) with an object-oriented approach and instructional error handling. STRling recognizes the cryptic nature of raw regular expression can be challenging and susceptibility to errors, which is why STRling looks and feels nothing like RegEx while maintaining the same power and flexibility. String validation should be simple and enjoyable, not a hassle. Best of all, STRling syntax is built upon the RegEx engine, making it fully compatible with all libraries that accept RegEx along with the traditional RegEx methods built
|
|
5
|
+
STRling is a next-generation production-grade syntax designed as a user interface for writing powerful regular expressions (RegEx) with an object-oriented approach and instructional error handling. STRling recognizes the cryptic nature of raw regular expression can be challenging and susceptibility to errors, which is why STRling looks and feels nothing like RegEx while maintaining the same power and flexibility. String validation should be simple and enjoyable, not a hassle. Best of all, STRling syntax is built upon the RegEx engine, making it fully compatible with all libraries that accept RegEx along with the traditional RegEx methods built-in to Python.
|
|
6
6
|
|
|
7
7
|
### Why STRling?
|
|
8
8
|
|
|
@@ -40,20 +40,20 @@ import re
|
|
|
40
40
|
# - 1234567890
|
|
41
41
|
|
|
42
42
|
# Separator: either space or hyphen
|
|
43
|
-
separator = s.in_(
|
|
43
|
+
separator = s.in_(' -')
|
|
44
44
|
|
|
45
45
|
# Optional area code part: 123 even if in parenthesis like (123)
|
|
46
46
|
area_code = s.merge( # notice we use merge since we don't want to name the group with parenthesis
|
|
47
|
-
s.may(
|
|
47
|
+
s.may('('), # Optional opening parenthesis
|
|
48
48
|
s.group('area_code', s.digit(3)), # Exactly 3 digits and named for later reference
|
|
49
|
-
s.may(
|
|
49
|
+
s.may(')') # Optional closing parenthesis
|
|
50
50
|
)
|
|
51
51
|
|
|
52
52
|
# Central part: 456
|
|
53
|
-
central_part = s.group('central_part', s.digit(3))
|
|
53
|
+
central_part = s.group('central_part', s.digit(3)) # Exactly 3 digits and named for later reference
|
|
54
54
|
|
|
55
55
|
# Last part: 7890
|
|
56
|
-
last_part = s.group("last_part", s.digit(4))
|
|
56
|
+
last_part = s.group("last_part", s.digit(4)) # Exactly 4 digits and named for later reference
|
|
57
57
|
|
|
58
58
|
# Combine all parts into the final phone number pattern
|
|
59
59
|
# Notice we don't name the whole pattern since we can already reference it
|
|
@@ -68,7 +68,7 @@ phone_number_pattern = s.merge(
|
|
|
68
68
|
# Example usage
|
|
69
69
|
# Note: To make a pattern a RegEx string compatible with other engines use `str(pattern)`.
|
|
70
70
|
example_text = "(123) 456-7890 and 123-456-7890"
|
|
71
|
-
pattern = re.compile(str(phone_number_pattern))
|
|
71
|
+
pattern = re.compile(str(phone_number_pattern)) # Notice str(pattern)
|
|
72
72
|
matches = pattern.finditer(example_text)
|
|
73
73
|
|
|
74
74
|
for match in matches:
|
|
@@ -108,13 +108,13 @@ import re
|
|
|
108
108
|
# For example, simply.letter(1, 3) will match 1 to 3 letters.
|
|
109
109
|
|
|
110
110
|
# But some methods take an unknown number of parameters and can't distinguish the range.
|
|
111
|
-
# For example, s.merge(simply.letter(), simply.digit(), 1, 2). <====
|
|
111
|
+
# For example, s.merge(simply.letter(), simply.digit(), 1, 2). <==== INVALID
|
|
112
112
|
|
|
113
|
-
# However, all methods allow setting the range by
|
|
113
|
+
# However, all methods allow setting the range by externally invoking unless otherwise specified.
|
|
114
114
|
# For example, simply.letter()(1, 2) is the same as simply.letter(1, 2).
|
|
115
115
|
|
|
116
116
|
# This external invocation may seem useless, but it can solve our earlier issue.
|
|
117
|
-
# For example, s.merge(simply.letter(), simply.digit())(1, 2). <====
|
|
117
|
+
# For example, s.merge(simply.letter(), simply.digit())(1, 2). <==== VALID
|
|
118
118
|
|
|
119
119
|
# Notice for all functions (where repetition is valid) we can invoke the range outside the parameters,
|
|
120
120
|
# but it is primarily useful for functions with an unknown number of parameters.
|
|
@@ -143,6 +143,18 @@ s.tab() # Matches a tab character.
|
|
|
143
143
|
s.carriage() # Matches a carriage return character.
|
|
144
144
|
s.bound() # Matches a boundary character.
|
|
145
145
|
|
|
146
|
+
####################
|
|
147
|
+
# Anchors
|
|
148
|
+
####################
|
|
149
|
+
|
|
150
|
+
s.start() # Matches the start of a line.
|
|
151
|
+
# There is no `simply.not_start()` function.
|
|
152
|
+
# Instead, use `simply.not_behind(simply.start())`.
|
|
153
|
+
|
|
154
|
+
s.end() # Matches the end of a line.
|
|
155
|
+
# There is no `simply.not_end()` function.
|
|
156
|
+
# Instead, use `simply.not_ahead(simply.end())`.
|
|
157
|
+
|
|
146
158
|
####################
|
|
147
159
|
# Custom Sets
|
|
148
160
|
####################
|
|
@@ -155,43 +167,26 @@ s.between(0, 9) # Matches any digit from 0 to 9.
|
|
|
155
167
|
s.between('a', 'z') # Matches any lowercase letter from 'a' to 'z'.
|
|
156
168
|
s.between('A', 'Z') # Matches any uppercase letter from 'A' to 'Z'.
|
|
157
169
|
|
|
158
|
-
# Matches any
|
|
159
|
-
s.in_(s.letter(), s.digit(),
|
|
160
|
-
#
|
|
161
|
-
# Key distinctions:
|
|
162
|
-
# - simply.in_() typically processes faster than simply.any_of().
|
|
163
|
-
# - simply.any_of() can process composite patterns while simply.in_() cannot.
|
|
164
|
-
# A composite pattern is one consisting of smaller combined patterns.
|
|
165
|
-
|
|
166
|
-
####################
|
|
167
|
-
# Anchors
|
|
168
|
-
####################
|
|
169
|
-
|
|
170
|
-
s.start() # Matches the start of a line.
|
|
171
|
-
# There is no `simply.not_start()` function.
|
|
172
|
-
# Instead, use `simply.not_behind(simply.start())`.
|
|
173
|
-
|
|
174
|
-
s.end() # Matches the end of a line.
|
|
175
|
-
# There is no `simply.not_end()` function.
|
|
176
|
-
# Instead, use `simply.not_ahead(simply.end())`.
|
|
170
|
+
# Matches any provided patterns, but they can't include subpatterns.
|
|
171
|
+
s.in_(s.letter(), s.digit(), ',.') # Matches any letter, digit, comma, and period.
|
|
172
|
+
# A composite pattern is one consisting of subpatterns (created by constructors and lookarounds).
|
|
177
173
|
|
|
178
174
|
####################
|
|
179
175
|
# Constructors
|
|
180
176
|
####################
|
|
181
177
|
|
|
182
|
-
s.any_of() # Matches any
|
|
183
|
-
#
|
|
184
|
-
#
|
|
185
|
-
|
|
186
|
-
|
|
187
|
-
# A composite pattern is one consisting of smaller combined patterns.
|
|
188
|
-
s.any_of(pattern1, pattern2) # Matches only if one of the patterns listed is present.
|
|
178
|
+
s.any_of() # Matches any pattern, including patterns consisting of subpatterns.
|
|
179
|
+
# A composite pattern is one consisting of subpatterns (created by constructors and lookarounds).
|
|
180
|
+
pattern1 = s.merge(s.digit(3), s.letter(3)) # Matches 3 digits followed by 3 letters.
|
|
181
|
+
pattern2 = s.merge(s.letter(3), s.digit(3)) # Matches 3 letters followed by 3 digits.
|
|
182
|
+
s.any_of(pattern1, pattern2) # Matches either pattern1 or pattern2
|
|
189
183
|
|
|
190
184
|
|
|
191
185
|
s.may() # Optionally matches the provided patterns.
|
|
192
186
|
# If a `may` pattern isn't there, it still will match the rest of the patterns.
|
|
193
|
-
# In the text, "ABC2" the patter below matches ['A', 'B', 'C2']
|
|
194
187
|
s.merge(s.letter(), s.may(s.digit()))
|
|
188
|
+
# Matches any letter, and includes any digit following the letter.
|
|
189
|
+
# In the text, "AB2" the pattern above matches 'A' and 'B2'.
|
|
195
190
|
|
|
196
191
|
|
|
197
192
|
s.merge() # Combines multiple patterns into one larger pattern.
|
|
@@ -202,12 +197,53 @@ s.capture() # Creates a numbered group that can be indexed for extracting part
|
|
|
202
197
|
# Capture is used the same as merge.
|
|
203
198
|
s.capture(s.letter(), s.digit())
|
|
204
199
|
|
|
200
|
+
# Captures CANNOT be invoked with a range: s.capture(s.digit(), s.letter())(1, 2) <== INVALID
|
|
201
|
+
# Captures CAN be invoked with a number of copies: s.capture(s.digit(), s.letter())(3) <== VALID
|
|
202
|
+
|
|
203
|
+
three_digit_group = s.capture(s.digit(3))
|
|
204
|
+
four_groups_of_three = three_digit_groups(4)
|
|
205
|
+
|
|
206
|
+
example_text = "Here is a number: 111222333444"
|
|
207
|
+
match = re.search(str(four_groups_of_three), example_text) # Notice str(pattern)
|
|
208
|
+
|
|
209
|
+
print("Full Match:", match.group())
|
|
210
|
+
print("First:", match.group(1))
|
|
211
|
+
print("Second:", match.group(2))
|
|
212
|
+
print("Third:", match.group(3))
|
|
213
|
+
print("Fourth:", match.group(4))
|
|
214
|
+
|
|
215
|
+
# Output:
|
|
216
|
+
# Full Match: 111222333444
|
|
217
|
+
# First: 111
|
|
218
|
+
# Second: 222
|
|
219
|
+
# Third: 333
|
|
220
|
+
# Fourth: 444
|
|
221
|
+
|
|
205
222
|
|
|
206
223
|
s.group() # Creates a named group that can be referenced for extracting part of a match.
|
|
207
224
|
# group is used the same as merge and capture but it takes a string name as the first argument.
|
|
208
225
|
s.group('my_group', s.letter(), s.digit())
|
|
209
|
-
|
|
226
|
+
|
|
227
|
+
# Unlike merge and capture, groups CANNOT be invoked with a range.
|
|
210
228
|
# This is because group names must be unique in a pattern.
|
|
229
|
+
# s.group('unique_name', s.digit())(1, 2) <== INVALID
|
|
230
|
+
|
|
231
|
+
# Groups can easily be referenced from the match by name
|
|
232
|
+
# assuming the numbers have been grouped and named properly.
|
|
233
|
+
example_text = "Here is a phone number: 123-456-7890."
|
|
234
|
+
match = re.search(str(phone_number_pattern), example_text) # Notice str(pattern)
|
|
235
|
+
|
|
236
|
+
print("Full Match:", match.group())
|
|
237
|
+
print("Area Code:", match.group("area_code"))
|
|
238
|
+
print("Central Part:", match.group("central_part"))
|
|
239
|
+
print("Last Part:", match.group("last_part"))
|
|
240
|
+
|
|
241
|
+
# Output:
|
|
242
|
+
# Full Match: 123-456-7890
|
|
243
|
+
# Area Code: 123
|
|
244
|
+
# Central Part: 456
|
|
245
|
+
# Last Part: 7890
|
|
246
|
+
|
|
211
247
|
|
|
212
248
|
####################
|
|
213
249
|
# Lookarounds
|
|
@@ -0,0 +1,211 @@
|
|
|
1
|
+
|
|
2
|
+
from .pattern import Pattern, clean_params
|
|
3
|
+
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
############################
|
|
7
|
+
# Constructor Methods
|
|
8
|
+
########
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
def any_of(*patterns):
|
|
12
|
+
"""
|
|
13
|
+
Matches any provided pattern, including patterns consisting of subpatterns.
|
|
14
|
+
|
|
15
|
+
Example: simply as s
|
|
16
|
+
pattern1 = s.merge(s.digit(3), s.letter(3)) # Matches 3 digits followed by 3 letters.
|
|
17
|
+
|
|
18
|
+
pattern2 = s.merge(s.letter(3), s.digit(3)) # Matches 3 letters followed by 3 digits.
|
|
19
|
+
|
|
20
|
+
either_pattern = s.any_of(pattern1, pattern2) # Matches either pattern1 or pattern2
|
|
21
|
+
|
|
22
|
+
Parameters:
|
|
23
|
+
- *patterns (Pattern/str): One or more patterns to be matched.
|
|
24
|
+
|
|
25
|
+
Returns:
|
|
26
|
+
- Pattern: A Pattern object representing the OR combination of the given patterns.
|
|
27
|
+
|
|
28
|
+
Raises:
|
|
29
|
+
- ValueError: If any of the parameters are not an instance of Pattern or str.
|
|
30
|
+
"""
|
|
31
|
+
|
|
32
|
+
clean_patterns = clean_params(*patterns)
|
|
33
|
+
|
|
34
|
+
joined = '|'.join(f'(?:{str(p)})' for p in clean_patterns)
|
|
35
|
+
new_pattern = f'(?:{joined})'
|
|
36
|
+
|
|
37
|
+
return Pattern(new_pattern, composite=True)
|
|
38
|
+
|
|
39
|
+
def may(*patterns):
|
|
40
|
+
"""
|
|
41
|
+
Optionally matches the provided patterns. If this pattern is absent, surrounding patterns can still match.
|
|
42
|
+
|
|
43
|
+
Example: simply as s
|
|
44
|
+
my_pattern = s.merge(s.letter(), s.may(s.digit()))
|
|
45
|
+
|
|
46
|
+
# Matches any letter, and includes any digit following the letter.
|
|
47
|
+
|
|
48
|
+
# In the text, "AB2" the pattern above matches 'A' and 'B2'.
|
|
49
|
+
|
|
50
|
+
Parameters:
|
|
51
|
+
- *patterns (Pattern/str): One or more patterns to be optionally matched.
|
|
52
|
+
|
|
53
|
+
Returns:
|
|
54
|
+
- Pattern: A Pattern object representing the optional match of the given patterns.
|
|
55
|
+
|
|
56
|
+
Raises:
|
|
57
|
+
- ValueError: If any of the parameters are not an instance of Pattern or str.
|
|
58
|
+
"""
|
|
59
|
+
|
|
60
|
+
clean_patterns = clean_params(*patterns)
|
|
61
|
+
|
|
62
|
+
joined = merge(*clean_patterns)
|
|
63
|
+
new_pattern = f'{joined}?'
|
|
64
|
+
|
|
65
|
+
return Pattern(new_pattern, composite=True)
|
|
66
|
+
|
|
67
|
+
|
|
68
|
+
|
|
69
|
+
def merge(*patterns):
|
|
70
|
+
"""
|
|
71
|
+
Combines the provided patterns into one larger pattern.
|
|
72
|
+
|
|
73
|
+
Example: simply as s
|
|
74
|
+
|
|
75
|
+
# Below matches any digit, comma, or period.
|
|
76
|
+
|
|
77
|
+
my_merged_pattern = s.merge(s.digit(), ',.')
|
|
78
|
+
|
|
79
|
+
Parameters:
|
|
80
|
+
- *patterns (Pattern/str): One or more patterns to be concatenated.
|
|
81
|
+
|
|
82
|
+
Returns:
|
|
83
|
+
- Pattern: A Pattern object representing the concatenation of the given patterns.
|
|
84
|
+
|
|
85
|
+
Raises:
|
|
86
|
+
- ValueError: If any of the parameters are not an instance of Pattern or str.
|
|
87
|
+
"""
|
|
88
|
+
|
|
89
|
+
clean_patterns = clean_params(*patterns)
|
|
90
|
+
|
|
91
|
+
joined = ''.join(str(p) for p in clean_patterns)
|
|
92
|
+
new_pattern = f'(?:{joined})'
|
|
93
|
+
|
|
94
|
+
return Pattern(new_pattern, composite=True)
|
|
95
|
+
|
|
96
|
+
def capture(*patterns):
|
|
97
|
+
"""
|
|
98
|
+
Creates a numbered group that can be indexed for extracting this part of the match.
|
|
99
|
+
|
|
100
|
+
Captures CANNOT be invoked with a range.
|
|
101
|
+
|
|
102
|
+
s.capture(s.digit(), s.letter())(1, 2) <== INVALID
|
|
103
|
+
|
|
104
|
+
Captures CAN be invoked with a number of copies.
|
|
105
|
+
|
|
106
|
+
s.capture(s.digit(), s.letter())(3) <== VALID
|
|
107
|
+
|
|
108
|
+
Example: simply as s
|
|
109
|
+
|
|
110
|
+
# Below matches any digit, comma, or period.
|
|
111
|
+
|
|
112
|
+
my_captured_pattern = s.capture(s.digit(), ',.')
|
|
113
|
+
|
|
114
|
+
|
|
115
|
+
Parameters:
|
|
116
|
+
- *patterns (Pattern/str): One or more patterns to be captured.
|
|
117
|
+
|
|
118
|
+
Returns:
|
|
119
|
+
- Pattern: A Pattern object representing the capturing group of the given patterns.
|
|
120
|
+
|
|
121
|
+
Raises:
|
|
122
|
+
- ValueError: If any of the parameters are not an instance of Pattern or str.
|
|
123
|
+
|
|
124
|
+
Referencing: simply as s
|
|
125
|
+
three_digit_group = s.capture(s.digit(3))
|
|
126
|
+
|
|
127
|
+
four_groups_of_three = three_digit_groups(4)
|
|
128
|
+
|
|
129
|
+
example_text = "Here is a number: 111222333444"
|
|
130
|
+
|
|
131
|
+
match = re.search(str(four_groups_of_three), example_text) # Notice str(pattern)
|
|
132
|
+
|
|
133
|
+
print("Full Match:", match.group())
|
|
134
|
+
print("First:", match.group(1))
|
|
135
|
+
print("Second:", match.group(2))
|
|
136
|
+
print("Third:", match.group(3))
|
|
137
|
+
print("Fourth:", match.group(4))
|
|
138
|
+
|
|
139
|
+
# Output:
|
|
140
|
+
# Full Match: 111222333444
|
|
141
|
+
# First: 111
|
|
142
|
+
# Second: 222
|
|
143
|
+
# Third: 333
|
|
144
|
+
# Fourth: 444
|
|
145
|
+
"""
|
|
146
|
+
|
|
147
|
+
clean_patterns = clean_params(*patterns)
|
|
148
|
+
|
|
149
|
+
joined = ''.join(str(p) for p in clean_patterns)
|
|
150
|
+
new_pattern = f'({joined})'
|
|
151
|
+
|
|
152
|
+
return Pattern(new_pattern, composite=True, numbered_group=True)
|
|
153
|
+
|
|
154
|
+
def group(name, *patterns):
|
|
155
|
+
"""
|
|
156
|
+
Creates a unique named group that can be referenced for extracting this part of the match.
|
|
157
|
+
|
|
158
|
+
Groups CANNOT be invoked with a range.
|
|
159
|
+
|
|
160
|
+
s.group('name', s.digit())(1, 2) <== INVALID
|
|
161
|
+
|
|
162
|
+
Example: simply as s
|
|
163
|
+
|
|
164
|
+
# Below matches any digit, comma, or period.
|
|
165
|
+
|
|
166
|
+
my_named_pattern = s.group('my_group', s.digit(), ',.')
|
|
167
|
+
|
|
168
|
+
Parameters:
|
|
169
|
+
- name (str): The name of the capturing group.
|
|
170
|
+
- *patterns (Pattern/str): One or more patterns to be captured.
|
|
171
|
+
|
|
172
|
+
Returns:
|
|
173
|
+
- Pattern: A Pattern object representing the named capturing group of the given patterns.
|
|
174
|
+
|
|
175
|
+
Raises:
|
|
176
|
+
- ValueError: If any of the parameters are not an instance of Pattern or str.
|
|
177
|
+
|
|
178
|
+
Referencing: simply as s
|
|
179
|
+
first = s.group("first", s.digit(3))
|
|
180
|
+
|
|
181
|
+
second = s.group("second", s.digit(3))
|
|
182
|
+
|
|
183
|
+
third = s.group("third", s.digit(4))
|
|
184
|
+
|
|
185
|
+
phone_number_pattern = s.merge(first, "-", second, "-", third)
|
|
186
|
+
|
|
187
|
+
example_text = "Here is a phone number: 123-456-7890."
|
|
188
|
+
|
|
189
|
+
match = re.search(str(phone_number_pattern), example_text) # Notice str(pattern)
|
|
190
|
+
|
|
191
|
+
print("Full Match:", match.group())
|
|
192
|
+
print("First:", match.group("first"))
|
|
193
|
+
print("Second:", match.group("second"))
|
|
194
|
+
print("Third:", match.group("third"))
|
|
195
|
+
|
|
196
|
+
# Output:
|
|
197
|
+
# Full Match: 123-456-7890
|
|
198
|
+
# First: 123
|
|
199
|
+
# Second: 456
|
|
200
|
+
# Third: 7890
|
|
201
|
+
"""
|
|
202
|
+
|
|
203
|
+
if not isinstance(name, str):
|
|
204
|
+
raise ValueError("The `name` parameter must be a string like 'my_group_name'.")
|
|
205
|
+
|
|
206
|
+
clean_patterns = clean_params(*patterns)
|
|
207
|
+
|
|
208
|
+
joined = ''.join(str(p) for p in clean_patterns)
|
|
209
|
+
new_pattern = f'(?P<{name}>{joined})'
|
|
210
|
+
|
|
211
|
+
return Pattern(new_pattern, composite=True, named_group=True)
|