Upload text_utils.py with huggingface_hub
Browse files- text_utils.py +20 -25
text_utils.py
CHANGED
|
@@ -1,9 +1,10 @@
|
|
|
|
|
| 1 |
import re
|
|
|
|
| 2 |
|
| 3 |
|
| 4 |
def split_words(s):
|
| 5 |
-
"""
|
| 6 |
-
Splits a string into words based on PascalCase, camelCase, snake_case, kebab-case, and numbers attached to strings.
|
| 7 |
|
| 8 |
Args:
|
| 9 |
s (str): The string to be split.
|
|
@@ -19,13 +20,11 @@ def split_words(s):
|
|
| 19 |
s = re.sub(r"([a-zA-Z])(\d)", r"\1 \2", s)
|
| 20 |
s = re.sub(r"(\d)([a-zA-Z])", r"\1 \2", s)
|
| 21 |
# Split the string into words based on spaces
|
| 22 |
-
|
| 23 |
-
return words
|
| 24 |
|
| 25 |
|
| 26 |
def is_camel_case(s):
|
| 27 |
-
"""
|
| 28 |
-
Checks if a string is in camelCase.
|
| 29 |
|
| 30 |
Args:
|
| 31 |
s (str): The string to be checked.
|
|
@@ -37,8 +36,7 @@ def is_camel_case(s):
|
|
| 37 |
|
| 38 |
|
| 39 |
def is_snake_case(s):
|
| 40 |
-
"""
|
| 41 |
-
Checks if a string is in snake_case.
|
| 42 |
|
| 43 |
Args:
|
| 44 |
s (str): The string to be checked.
|
|
@@ -50,8 +48,7 @@ def is_snake_case(s):
|
|
| 50 |
|
| 51 |
|
| 52 |
def camel_to_snake_case(s):
|
| 53 |
-
"""
|
| 54 |
-
Converts a string from camelCase to snake_case.
|
| 55 |
|
| 56 |
Args:
|
| 57 |
s (str): The string to be converted.
|
|
@@ -65,16 +62,11 @@ def camel_to_snake_case(s):
|
|
| 65 |
# Ensure there's an underscore before any uppercase letter that's followed by a lowercase letter or digit and comes after a sequence of uppercase letters
|
| 66 |
s = re.sub(r"([A-Z]+)([A-Z][a-z0-9])", r"\1_\2", s)
|
| 67 |
|
| 68 |
-
|
| 69 |
-
return s
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
import shutil
|
| 73 |
|
| 74 |
|
| 75 |
def print_dict(d, indent=0, indent_delta=4, max_chars=None):
|
| 76 |
-
"""
|
| 77 |
-
Prints a dictionary in a formatted manner, taking into account the terminal width.
|
| 78 |
|
| 79 |
Args:
|
| 80 |
d (dict): The dictionary to be printed.
|
|
@@ -82,13 +74,15 @@ def print_dict(d, indent=0, indent_delta=4, max_chars=None):
|
|
| 82 |
indent_delta (int, optional): The amount of spaces to add for each level of indentation. Defaults to 4.
|
| 83 |
max_chars (int, optional): The maximum number of characters for each line. Defaults to terminal width - 10.
|
| 84 |
"""
|
| 85 |
-
max_chars =
|
|
|
|
|
|
|
| 86 |
indent_str = " " * indent
|
| 87 |
indent_delta_str = " " * indent_delta
|
| 88 |
|
| 89 |
for key, value in d.items():
|
| 90 |
if isinstance(value, dict):
|
| 91 |
-
|
| 92 |
print_dict(value, indent=indent + indent_delta, max_chars=max_chars)
|
| 93 |
else:
|
| 94 |
# Value is not a dict, print as a string
|
|
@@ -97,21 +91,22 @@ def print_dict(d, indent=0, indent_delta=4, max_chars=None):
|
|
| 97 |
line_width = max_chars - indent
|
| 98 |
# Split value by newline characters and handle each line separately
|
| 99 |
lines = str_value.split("\n")
|
| 100 |
-
|
| 101 |
for line in lines:
|
| 102 |
if len(line) + len(indent_str) + indent_delta > line_width:
|
| 103 |
# Split long lines into multiple lines
|
| 104 |
-
|
| 105 |
for i in range(line_width, len(line), line_width):
|
| 106 |
-
|
|
|
|
|
|
|
| 107 |
else:
|
| 108 |
-
|
| 109 |
key = "" # Empty the key for lines after the first one
|
| 110 |
|
| 111 |
|
| 112 |
def nested_tuple_to_string(nested_tuple: tuple) -> str:
|
| 113 |
-
"""
|
| 114 |
-
Converts a nested tuple to a string, with elements separated by underscores.
|
| 115 |
|
| 116 |
Args:
|
| 117 |
nested_tuple (tuple): The nested tuple to be converted.
|
|
|
|
| 1 |
+
import logging
|
| 2 |
import re
|
| 3 |
+
import shutil
|
| 4 |
|
| 5 |
|
| 6 |
def split_words(s):
|
| 7 |
+
"""Splits a string into words based on PascalCase, camelCase, snake_case, kebab-case, and numbers attached to strings.
|
|
|
|
| 8 |
|
| 9 |
Args:
|
| 10 |
s (str): The string to be split.
|
|
|
|
| 20 |
s = re.sub(r"([a-zA-Z])(\d)", r"\1 \2", s)
|
| 21 |
s = re.sub(r"(\d)([a-zA-Z])", r"\1 \2", s)
|
| 22 |
# Split the string into words based on spaces
|
| 23 |
+
return s.split()
|
|
|
|
| 24 |
|
| 25 |
|
| 26 |
def is_camel_case(s):
|
| 27 |
+
"""Checks if a string is in camelCase.
|
|
|
|
| 28 |
|
| 29 |
Args:
|
| 30 |
s (str): The string to be checked.
|
|
|
|
| 36 |
|
| 37 |
|
| 38 |
def is_snake_case(s):
|
| 39 |
+
"""Checks if a string is in snake_case.
|
|
|
|
| 40 |
|
| 41 |
Args:
|
| 42 |
s (str): The string to be checked.
|
|
|
|
| 48 |
|
| 49 |
|
| 50 |
def camel_to_snake_case(s):
|
| 51 |
+
"""Converts a string from camelCase to snake_case.
|
|
|
|
| 52 |
|
| 53 |
Args:
|
| 54 |
s (str): The string to be converted.
|
|
|
|
| 62 |
# Ensure there's an underscore before any uppercase letter that's followed by a lowercase letter or digit and comes after a sequence of uppercase letters
|
| 63 |
s = re.sub(r"([A-Z]+)([A-Z][a-z0-9])", r"\1_\2", s)
|
| 64 |
|
| 65 |
+
return s.lower()
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
|
| 67 |
|
| 68 |
def print_dict(d, indent=0, indent_delta=4, max_chars=None):
|
| 69 |
+
"""Prints a dictionary in a formatted manner, taking into account the terminal width.
|
|
|
|
| 70 |
|
| 71 |
Args:
|
| 72 |
d (dict): The dictionary to be printed.
|
|
|
|
| 74 |
indent_delta (int, optional): The amount of spaces to add for each level of indentation. Defaults to 4.
|
| 75 |
max_chars (int, optional): The maximum number of characters for each line. Defaults to terminal width - 10.
|
| 76 |
"""
|
| 77 |
+
max_chars = (
|
| 78 |
+
max_chars or shutil.get_terminal_size()[0] - 10
|
| 79 |
+
) # Get terminal size if max_chars not set
|
| 80 |
indent_str = " " * indent
|
| 81 |
indent_delta_str = " " * indent_delta
|
| 82 |
|
| 83 |
for key, value in d.items():
|
| 84 |
if isinstance(value, dict):
|
| 85 |
+
logging.info(f"{indent_str}{key}:")
|
| 86 |
print_dict(value, indent=indent + indent_delta, max_chars=max_chars)
|
| 87 |
else:
|
| 88 |
# Value is not a dict, print as a string
|
|
|
|
| 91 |
line_width = max_chars - indent
|
| 92 |
# Split value by newline characters and handle each line separately
|
| 93 |
lines = str_value.split("\n")
|
| 94 |
+
logging.info(f"{indent_str}{key} ({type(value).__name__}):")
|
| 95 |
for line in lines:
|
| 96 |
if len(line) + len(indent_str) + indent_delta > line_width:
|
| 97 |
# Split long lines into multiple lines
|
| 98 |
+
logging.info(f"{indent_str}{indent_delta_str}{line[:line_width]}")
|
| 99 |
for i in range(line_width, len(line), line_width):
|
| 100 |
+
logging.info(
|
| 101 |
+
f"{indent_str}{indent_delta_str}{line[i:i+line_width]}"
|
| 102 |
+
)
|
| 103 |
else:
|
| 104 |
+
logging.info(f"{indent_str}{indent_delta_str}{line}")
|
| 105 |
key = "" # Empty the key for lines after the first one
|
| 106 |
|
| 107 |
|
| 108 |
def nested_tuple_to_string(nested_tuple: tuple) -> str:
|
| 109 |
+
"""Converts a nested tuple to a string, with elements separated by underscores.
|
|
|
|
| 110 |
|
| 111 |
Args:
|
| 112 |
nested_tuple (tuple): The nested tuple to be converted.
|