mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-02 18:06:57 +00:00
766d900a41
### What problem does this PR solve? - rename rmSpace to remove_redundant_spaces - move clean_markdown_block to common module - add unit tests for remove_redundant_spaces and clean_markdown_block ### Type of change - [x] Refactoring --------- Signed-off-by: Jin Hai <haijin.chn@gmail.com>
74 lines
2.8 KiB
Python
74 lines
2.8 KiB
Python
#
|
|
# Copyright 2025 The InfiniFlow Authors. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
import re
|
|
|
|
|
|
def remove_redundant_spaces(txt: str):
|
|
"""
|
|
Remove redundant spaces around punctuation marks while preserving meaningful spaces.
|
|
|
|
This function performs two main operations:
|
|
1. Remove spaces after left-boundary characters (opening brackets, etc.)
|
|
2. Remove spaces before right-boundary characters (closing brackets, punctuation, etc.)
|
|
|
|
Args:
|
|
txt (str): Input text to process
|
|
|
|
Returns:
|
|
str: Text with redundant spaces removed
|
|
"""
|
|
# First pass: Remove spaces after left-boundary characters
|
|
# Matches: [non-alphanumeric-and-specific-right-punctuation] + [non-space]
|
|
# Removes spaces after characters like '(', '<', and other non-alphanumeric chars
|
|
# Examples:
|
|
# "( test" → "(test"
|
|
txt = re.sub(r"([^a-z0-9.,\)>]) +([^ ])", r"\1\2", txt, flags=re.IGNORECASE)
|
|
|
|
# Second pass: Remove spaces before right-boundary characters
|
|
# Matches: [non-space] + [non-alphanumeric-and-specific-left-punctuation]
|
|
# Removes spaces before characters like non-')', non-',', non-'.', and non-alphanumeric chars
|
|
# Examples:
|
|
# "world !" → "world!"
|
|
return re.sub(r"([^ ]) +([^a-z0-9.,\(<])", r"\1\2", txt, flags=re.IGNORECASE)
|
|
|
|
|
|
def clean_markdown_block(text):
|
|
"""
|
|
Remove Markdown code block syntax from the beginning and end of text.
|
|
|
|
This function cleans Markdown code blocks by removing:
|
|
- Opening ```Markdown tags (with optional whitespace and newlines)
|
|
- Closing ``` tags (with optional whitespace and newlines)
|
|
|
|
Args:
|
|
text (str): Input text that may be wrapped in Markdown code blocks
|
|
|
|
Returns:
|
|
str: Cleaned text with Markdown code block syntax removed, and stripped of surrounding whitespace
|
|
|
|
"""
|
|
# Remove opening ```markdown tag with optional whitespace and newlines
|
|
# Matches: optional whitespace + ```markdown + optional whitespace + optional newline
|
|
text = re.sub(r'^\s*```markdown\s*\n?', '', text)
|
|
|
|
# Remove closing ``` tag with optional whitespace and newlines
|
|
# Matches: optional newline + optional whitespace + ``` + optional whitespace at end
|
|
text = re.sub(r'\n?\s*```\s*$', '', text)
|
|
|
|
# Return text with surrounding whitespace removed
|
|
return text.strip()
|