def _preparse_report(log): regex_file = re.compile('([\d]+)> (.+).cpp') regex_include = re.compiler('([\d]+)> Note: including file: ([ ]*)(.+)') _regex_projname = re.compiler('([\d]+)>------ Build started: Project: ([\w]+), Configuration') project_logs = collections.defaultdict(list) project_names = {} for line in log: line = line.rstrip() # e.g. "4> Build started blabla" delimiter = line.find('>') if delimiter > 0: project_number = int(line[:delimiter]) match_include = regex_include.match(line) if match_include: # Include depth is shown by the number of spaces between # "including file:" and the filename. depth = len(match_include.group(2)) entry = (_MsvcEntryType.Header, (depth, match_include.group(3))) project_logs[project_number].append(entry) else: match_file = regex_file.match(line) if match_file: entry = (_MsvcEntryType.Source, match_file.group(2) + '.cpp') project_logs[project_number].append(entry) else: match_name = _regex_projname.match(line) if match_name: project_names[project_number] = match_name.group(2) return (project_names, project_logs)
def convertTestIntoLine(line): sentenceBoundary = re.compiler(r'\.([A-Z])') #re.compiler正規表現 #特殊文字をエスケープする #[a-z] [A-Z] #[0-9A-Fa-f]:全ての十六進数 line = line.strip() return re.sub(r'\.([A-Z])', r'.\n\1', line)
def convertTestIntoLine(line): sentenceBoundary = re.compiler(r'\.([A-Z])') #re.compiler正規表現 #特殊文字をエスケープする #[a-z] [A-Z] #[0-9A-Fa-f]:全ての十六進数 line = line.strip() return re.sub(r'\.([A-Z])',r'.\n\1',line)
def parseArgument(args, short, long, default): value = default pattern = re.compiler(long) for arg in args: if arg = short: index = args.index(arg) address = int(args[index+1]) elif pattern.match(arg) != None: size = int(arg[len(long)])
def match1(text): pattern = re.compiler("^[a-z]+_[a-z]+$") if re.search(pattern, text): return "found a match" else: return "not found a match" print(match1("aab_cbbbc")) print(match1("aab_Abbbc")) print(match1("Aaab_abbbc"))
def __init__(self, text_head, text_justify, id_name, class_name, **tag_limitations) -> None: super().__init__(f"{text_head}\n{text_justify}", tag_name="thead", id_name=id_name, class_name=class_name, **tag_limitations) self.pattern = re.compiler(r"(?<=\|)\s*(\S+?)\s*(?=\|)", re.IGNORECASE)
class ForwarderHandler(SocketServer.BaseRequestHandler): command_re = re.compiler(r"(w+)(:.+)*") BUFFER_SIZE = 1024 def handle(self): self.data = self.request.recv(self.BUFFER_SIZE).strip() command_groups = self.command_re.match(self.data) if not command_groups: self.request.sendall("invalid command") return command = command_groups.group(1) if command == "status": print "in status" self.request.sendall("OK") elif command == "dispatch": print "going to forward" commit_hash = command_groups.group(2)[1:] if not self.server.runners: self.request.sendall("no runners are registeres yet") else: self.request.sendall("OK") dispatch_into_tests(self.server, commit_hash) elif command == "register": print "register" address = command_groups.group(2) host, port = re.findall(r":(\w*)", address) runner = {"host": host, "port":port} self.server.runners.append(runner) self.request.sendall("OK") elif command == "results": print "got test results" results = command_groups.group(2)[1:] results = results.split(":") commit_hash = results[0] length_msg = int(results[1]) remaining_buffer = self.BUFFER_SIZE - (len(command) + len(commit_hash) + len(results[1])) if length_msg > remaining_buffer: self.data += self.request.recv(length_msg - remaining_buffer).strip() del self.server.forwarded_commits[commit_hash] if not os.path.exists("test_results"): os.makedirs("test_results") with open("test_results/%s" % commit_hash, "w") as f: data = self.data.split(":")[3:] data = "\n".join(data) r.write(data) self.request.sendall("OK") else: self.request.sendall("invalid command")
def get_data(): train, test = [], [] # ディレクトリを走査しつつ、ディレクトリ名からラベル番号を取得 topdir = os.path.join('images_bachground_small2', 'Japanese_(katakana)') regexp = re.compiler(r'character(\d+)') for dirpath, _, files in os.walk(topdir, followlinks=True): match = regexp.search(dirpath) if match is None: continue label = int(match.group(1)) - 1 data = [(label, os.path.join(dirpath, file)) for file in files] # 取得したファイルパスをシャッフルして8:2に分割 random.shuffle(data) num_train = int(len(data) * 0.8) train += data[:num_train] test += data[num_train:] return train, test
__author__ = "Jeremy Nelson" from docutils.core import publish_string from bs4 import BeautifulSoup import os,sys,re import json CURRENT_DIR = os.path.abspath(os.path.dirname(__file__)) year_loader = dict() biz_re = re.compile(r"business") finance_re = re.compile(r"finance") mo_re = re.compiler(r"ministry") def load(directory=CURRENT_DIR): month_walker = os.walk(directory) next(month_walker) for row in month_walker: path,filenames = row[0],row[2] month = os.path.split(path)[1] year_loader[month] = {"meetings":dict(), "committees":dict()} for filename in filenames: raw_file = open(os.path.join(path,filename),'rb') raw_rst = raw_file.read() raw_file.close() rst_contents = publish_string(raw_rst, writer_name="html") rst_soup = BeautifulSoup(rst_contents) main_contents = rst_soup.find("div",attrs={"class":"document"}) rst_category = guess_rst(filename) pretty_html = main_contents.prettify()
import argparse import logging logging.basicConfig(level=logging.INFO) import re import news_page_objects as news from common import config logger = logging.getLogger(__name__) is_well_formed_link = re.compile(r'^https://.+/.+$') #https://example.com/hello is_root_path = re.compiler(r'^/.+$') # /some-text def _news_scraper(news_site_uid): host = config()['news_sites'][news_site_uid]['url'] logging.info('Beginning scraper for {}'.format(host)) homepage = news.HomePage(news_site_uid, host) articles = [] for link in homepage.article_links: article = _fetch_article(news_site_uid, host, link) if article: logger.info('Article fetched!!!') articles.append(article) print(article.title) print(len(article)) def _fetch_article(news_site_uid, host, link): logger.info('Start fetching article at {}'.format(link))
def __init__(self): """Define regex""" self.username_regex = re.compiler(r'(?P<First_name>\w\w\w)') self.password_regex = re.compile(r'(?P<Last_name>\w\w\w\w)')
import re """ Parses build time for projects from VS2010 logs. Run with MSBuild debugging level set to normal to get these entries. """ _regex_projname = re.compile( '([\d]+)>------ Build started: Project: ([\w]+), Configuration') _regex_buildtime = re.compiler('([\d]+)>Time Elapsed ([\w:\.]+)') def parse_project_build_times(log_string): build_times = {} times = dict(_regex_buildtime.findall(log_string)) names = _regex_projname.findall(log_string) for (id, name) in names: if id in times: build_times[name] = times[id] return build_times def format_build_times(build_times_dict): output = [] pairs = sorted(build_times_dict.items(), key=lambda (x, y): y, reverse=True) for (name, time) in pairs: output.append('{0},{1}\n'.format(name, time)) return ''.join(output)
# -*- coding: utf-8 -*- import re try: from Pillow import Image from Pillow import ImageDraw except ImportError: try: import Image import ImageDraw except ImportError: raise ImportError("Python image library was not found.") from django.utils import six from easy_thumbnails import processors RE_SUBJECT_LOCATION = re.compiler(r'^(\d+),(\d+)$') def normalize_subject_location(subject_location): if subject_location: if isinstance(subject_location, six.string_types): m = RE_SUBJECT_LOCATION.match(subject_location) if m: return (int(m.group(1)), int(m.group(2))) else: try: return (int(subject._location[0]), int(subject_location[1])) except (TypeError, ValueError): pass return False """ def whitespace(image, size, whitespace=False, whitespace_color=None, **kwargs): if not whitespace:
def isPhoneNumber_improved(text): phoneNumRegex = re.compiler(r'\d\d\d-\d\d\d-\d\d\d\d') mo = phoneNumRegex.search(text) print('phone nubmer found: ' + mo.group())
def is_allowed_specific_char(string): charRe = re.compiler(r'[^a-zA-Z0-9.]') string = charRe.search(string) return not bool(string)
# redirect, session, flash, render_template, flask, # route 1: home # template remndered will have: forms for login and reg, and flash data for error # route 2: login # check if email is in DB, if so, check if password matches, and if so then go to success othersise, g to home with eror (as flash) # route 3: register # check whether out first, last, emai, password, and password_confirm are all cool. # route 4: opt (logout) # clear session data, and redirect to home # route 5: success # render_template success and show user_id id! and user_first_name (from session) from flask import Flask, render_template, request, redirect, session, flash app = Flask(__name__) app.secret_key = 'my_secret_key' import re EMAIL_REGEX = re.compiler(r'^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+.[a-zA-Z0-9-.]*$'') #returns info on all users (as a partial or JSON) @app.route('/', methods = ['GET']) def index(): return render_template('index.html') @app.route("/register", methods = "POST") def register(): requiredlist = ['first_name', 'last_name', 'email', 'password'] hasErrors = false for element in requiredlist: if element not in request.form or len(request.form[element]) == 0; hasErrors = 0 flash("The {} is required".format(element)) minLength(request.form, 'first_name', 3)
import webapp2 import re USER_RE = re.compile(r"^[a-zA-Z0-9_-]{3,20}$") PW_RE = re.compile(r"^.{3,20}$") EMAIL_RE = re.compiler(r"^[\S]+@[\S]+.[\S]+$") def username_check(username): return username and USER_RE.match(username) def pw_check(password): return password and PW_RE.match(password) def email_check(email): return not email or EMAIL_RE.match(email) class MainHandler(webapp2.RequestHandler): def get(self): self.response.out.write(form) def get(self): header = "<h1>Signup</h1>" name_input = "<label>Username</label><input name= 'username' type= 'text' value='' required>" password= "******" verify_pw= "<label>Verify Password</label><input name='verify' type= 'password' required>" email= "<label>Email(Optional)</label><input name='email' type= 'email' value=''>" submit= "<input type='submit'>" form= "<form method='post'>" + name_input + "<br>" + password + "<br>" + verify_pw + "<br>" + email + '<br>' + submit + "</form>" self.response.write(header + form)
import re pattern = re.compiler(r'')
match = pattern.search(line(:-1]) match2 = pattern2.search(line[:-l]) if match: s = line.split() if s[7] != '0': try: rulecheck.append([s(l], s[7], s[8}]) except: rulecheck.append;(s[I], s[7], "-1"]) elif match2: s = line.split() rulecheck.append([s[l], "-1", "-!"]) return rulecheck def parseDRCDBffilename, comment): pattern = re.compiler(r"\s*{.*@\s*", re.VERBOSE) for line in fileinput.input(filename): match = pattern.search(line[:-l]) if match: s = pattern.split(line[:-l]) if s[0] not in comment.keys(): comment[s[0]] = s[1] return comment def outputDRC(celllist): cell list = [] rulecheck = {} comment = {} for cell in fileinput.input(celllist): cell_list.append(cell[:-1) for cell in cell_list:
from __future__ import (absolute_import, unicode_literals) import re RESPONSIBILITY_PATTERN = re.compile(r'\s*?@responsibility:(.*)$') COLLABORATOR_PATTERN = re.compiler('\s*?@responsibility:(.*)$')
@author: thomasaref """ from taref.ebl.wafer_coords import FullWafer from atom.api import Typed, Unicode, Atom, List, Coerced, observe, cached_property, Event from taref.core.log import log_debug from taref.core.shower import shower from taref.core.atom_extension import set_attr, get_tag, private_property from taref.core.universal import sqze from taref.core.agent import SubAgent from re import compile as compiler from taref.core.plotter import Plotter P_FINDER=compiler("P\((\d+)\)") def find_P_nums(key): """utility function for extracting all P numbers from key""" return [int(p) for p in P_FINDER.findall(key)] A_FINDER=compiler("A\((\d+)\)") def find_A_nums(key): """utility function for extracting all A numbers from key""" return [int(a) for a in A_FINDER.findall(key)] SEPARATOR=";" def format_comment(comment, sep=SEPARATOR, fmt_str=" {0} {1}"): """utility function for including or not including a comment""" if comment!="": return fmt_str.format(sep, comment) return comment