# 簡單查找
text = "Python is amazing for text processing"
start = text.find("amazing")  # 返回10
contains = "text" in text  # True

# 更靈活的startswith/endswith
if text.startswith(("Python", "Java")):
    print("Programming language related")

# 多行文本處理技巧
multiline = """First line
Second line
Third line"""
match = any(line.startswith('Second') for line in multiline.splitlines())

import re

log_entry = "[2023-08-15 14:30:22] ERROR: Database connection failed"
pattern = r"\[(?P<date>\d{4}-\d{2}-\d{2})\s+(?P<time>\d{2}:\d{2}:\d{2})\]\s+(?P<level>\w+):\s+(?P<message>.+)"

match = re.match(pattern, log_entry)
if match:
    # 通過命名分組直接訪問
    error_info = {
        "timestamp": f"{match.group('date')}T{match.group('time')}",
        "level": match.group('level'),
        "message": match.group('message')
    }

# 錯誤方式（每次調(diào)用都編譯）
for line in logs:
    re.search(r'\d+', line)

# 正確方式（預(yù)編譯）
digit_pattern = re.compile(r'\d+')
for line in logs:
    digit_pattern.search(line)

# 低效寫法：回溯陷阱
re.search(r'<.*?>', html) 

# 高效寫法：排除匹配
re.search(r'<[^>]+>', html)

import re

pattern = re.compile(r'\b[A-Z]{3}\d{6}\b')  # 匹配股票代碼

def find_stock_codes(file_path):
    with open(file_path, 'r', encoding='utf-8') as f:
        for line_num, line in enumerate(f, 1):
            for match in pattern.finditer(line):
                yield {
                    "code": match.group(),
                    "line": line_num,
                    "position": match.start()
                }

# 處理GB級文件示例
for result in find_stock_codes("financial_report.txt"):
    process(result)

from collections import defaultdict
import re

class MultipatternScanner:
    def __init__(self, pattern_dict):
        self.patterns = {
            name: re.compile(pattern) 
            for name, pattern in pattern_dict.items()
        }
        self.results = defaultdict(list)
    
    def scan(self, text):
        for name, pattern in self.patterns.items():
            for match in pattern.finditer(text):
                self.results[name].append(match.group())
        return self.results

# 監(jiān)控系統(tǒng)告警掃描
patterns = {
    "critical": r"CRITICAL:.+?",
    "warning": r"WARNING:.+?",
    "error": r"ERROR:.+?"
}
scanner = MultipatternScanner(patterns)
alerts = scanner.scan(log_content)

def parse_ini(text):
    current_section = None
    config = {}
    
    for line in text.splitlines():
        # 處理段標(biāo)題
        if section_match := re.match(r'^\s*\[(.*?)\]\s*$', line):
            current_section = section_match.group(1)
            config[current_section] = {}
        
        # 處理鍵值對
        elif key_match := re.match(r'^\s*([\w\-]+)\s*=\s*(.*?)\s*$', line):
            if not current_section:
                raise SyntaxError("Key outside section")
            key, value = key_match.groups()
            config[current_section][key] = value
            
    return config

# 示例INI解析
ini_content = """
[network]
host = 192.168.1.1
port = 8080
"""
network_config = parse_ini(ini_content)["network"]

from pyparsing import Word, alphas, Group, Suppress, Combine, nums

# 定義日志元素
timestamp = Combine(Word(nums) + '-' + Word(nums) + '-' + Word(nums) + 
                   Word(nums) + ':' + Word(nums) + ':' + Word(nums))
log_level = Word(alphas.upper())
message = Word(alphas + ' ')

# 構(gòu)建日志解析器
log_parser = (
    Suppress('[') + timestamp.setResultsName('timestamp') + Suppress(']') +
    log_level.setResultsName('level') + Suppress(':') + 
    message.setResultsName('message')
)

# 應(yīng)用解析
sample = "[2023-08-15 14:30:22] ERROR: Connection timeout"
parsed = log_parser.parseString(sample)
print(f"{parsed.timestamp} | {parsed.level} | {parsed.message}")

import spacy
from spacy.matcher import Matcher

nlp = spacy.load("en_core_web_sm")
matcher = Matcher(nlp.vocab)

# 匹配程度副詞+形容詞組合
pattern = [
    {"POS": {"IN": ["ADV", "DET"]}, "OP": "*"},
    {"POS": "ADJ"}
]
matcher.add("INTENSITY_ADJ", [pattern])

doc = nlp("This is an extremely interesting and really long text")
matches = matcher(doc)

for match_id, start, end in matches:
    print(doc[start:end].text)
# 輸出：extremely interesting, really long

import re
from spacy.matcher import Matcher

nlp = spacy.load("en_core_web_sm")
matcher = Matcher(nlp.vocab)

# 正則處理數(shù)字部分
dosage_pattern = r"(\d+\s?-\s?\d+|\d+)\s?(mg|g|ml)"

# Spacy處理文本結(jié)構(gòu)
matcher.add("DOSAGE", [
    {"LOWER": {"IN": ["take", "administer", "prescribe"]}},
    {"POS": "DET", "OP": "?"},
    {"TEXT": {"REGEX": dosage_pattern}}
])

text = "The patient should take 2-3 tablets of 200 mg each day"
doc = nlp(text)
matches = matcher(doc)

# 危險的正則 - 易受ReDos攻擊
dangerous_re = r"^(a+)+$"

# 惡意輸入導(dǎo)致超長匹配時間
malicious_input = "a" * 100 + "!"

# 防范措施：
# 1. 避免復(fù)雜嵌套量詞
# 2. 使用regex庫的安全模式
import regex
safe_re = regex.compile(r"^(a+)+$", regex.VERSION1)

# 3. 設(shè)置超時保護
safe_re = re.compile(dangerous_re)
try:
    safe_re.match(malicious_input, timeout=0.5)  # 0.5秒超時
except TimeoutError:
    print("Pattern too complex")