Menu

[8f66b6]: / fulltextindex / SearchMethods.py  Maximize  Restore  History

Download this file

149 lines (127 with data), 6.8 kB

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
# -*- coding: utf-8 -*-
"""
Copyright (C) 2020 Oliver Tengler
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
"""
import os
import re
import threading
from typing import Optional, List
from tools.FileTools import fopen
from . import FullTextIndex, IndexConfiguration, Query, IndexUpdater
emptyPattern = re.compile("") # make mypy happy
class ResultSet:
def __init__(self, matches: FullTextIndex.SearchResult = None, searchData: Query.Query = None,
perfReport: FullTextIndex.PerformanceReport = None, label: str = None) -> None:
self.matches = matches or []
self.perfReport = perfReport
self.searchData = searchData
self.label = label
class SearchMethods:
"""
Holds an instance of FullTextIndex. Setting the instance is secured by a lock because
the call to 'cancel' may happen any time - also during construction and assignment of FullTextIndex
"""
def __init__(self) -> None:
self.fti: Optional[FullTextIndex.FullTextIndex] = None
self.lock = threading.Lock()
def searchContent(self, searchData: FullTextIndex.ContentQuery, indexConf: IndexConfiguration.IndexConfiguration,
commonKeywordMap:FullTextIndex.CommonKeywordMap, cancelEvent: threading.Event=None) -> ResultSet:
try:
if indexConf.isContentIndexed():
return self.__searchContentIndexed(searchData, indexConf, commonKeywordMap, cancelEvent)
return self.__searchContentDirect(searchData, indexConf, cancelEvent)
finally:
with self.lock:
del self.fti
self.fti = None
def __searchContentIndexed(self, searchData: FullTextIndex.ContentQuery, indexConf: IndexConfiguration.IndexConfiguration,
commonKeywordMap:FullTextIndex.CommonKeywordMap, cancelEvent: threading.Event=None) -> ResultSet:
perfReport = FullTextIndex.PerformanceReport()
with perfReport.newAction("Init database"):
with self.lock:
self.fti = FullTextIndex.FullTextIndex(indexConf.indexdb)
result = ResultSet(self.fti.searchContent(searchData, perfReport, commonKeywordMap, cancelEvent=cancelEvent), searchData, perfReport)
return result
def __searchContentDirect(self, searchData: FullTextIndex.ContentQuery, indexConf: IndexConfiguration.IndexConfiguration, cancelEvent: threading.Event=None) -> ResultSet:
matches: List[str] = []
for directory in indexConf.directories:
for dirName, fileName in IndexUpdater.genFind(indexConf.extensions, directory, indexConf.dirExcludes):
file = os.path.join(dirName, fileName)
if searchData.matchFolderAndExtensionFilter(file):
with fopen(file) as inputFile:
for _ in searchData.matches(inputFile.read()):
matches.append(file)
break
if cancelEvent and cancelEvent.is_set():
return ResultSet([], searchData)
matches = removeDupsAndSort(matches)
return ResultSet(matches, searchData)
def searchFileName(self, searchData: FullTextIndex.FileQuery, indexConf: IndexConfiguration.IndexConfiguration, cancelEvent: threading.Event=None) -> ResultSet:
try:
if indexConf.isFileNameIndexed():
return self.__searchFileNameIndexed(searchData, indexConf, cancelEvent)
return self.__searchFileNameDirect(searchData, indexConf, cancelEvent)
finally:
with self.lock:
del self.fti
self.fti = None
def __searchFileNameIndexed(self, searchData: FullTextIndex.FileQuery, indexConf: IndexConfiguration.IndexConfiguration, cancelEvent: threading.Event=None) -> ResultSet:
perfReport = FullTextIndex.PerformanceReport()
with perfReport.newAction("Init database"):
with self.lock:
self.fti = FullTextIndex.FullTextIndex(indexConf.indexdb)
result = ResultSet(self.fti.searchFile(searchData, perfReport, cancelEvent=cancelEvent), searchData, perfReport)
return result
def __searchFileNameDirect(self, searchData: FullTextIndex.FileQuery, indexConf: IndexConfiguration.IndexConfiguration, cancelEvent: threading.Event=None) -> ResultSet:
search = searchData.search
searchLower = search.lower()
hasWildcards = Query.hasFileNameWildcard(search)
bCaseSensitive = searchData.bCaseSensitive
searchPattern = emptyPattern
if hasWildcards:
reFlags = 0
if not bCaseSensitive:
reFlags = re.IGNORECASE
searchPattern = re.compile(Query.createPathMatchPattern(search, True), reFlags)
matches: List[str] = []
for directory in indexConf.directories:
for dirName, fileName in IndexUpdater.genFind(indexConf.extensions, directory, indexConf.dirExcludes):
fullPath = os.path.join(dirName, fileName)
name,_ = os.path.splitext(fileName)
if not hasWildcards:
if bCaseSensitive:
if name != search:
continue
else:
if name.lower() != searchLower:
continue
elif not searchPattern.match(name):
continue
if searchData.matchFolderAndExtensionFilter(fullPath): # TODO: splits file name again
matches.append(fullPath)
if cancelEvent and cancelEvent.is_set():
return ResultSet([], searchData)
matches.sort()
return ResultSet(matches, searchData)
def cancel(self) -> None:
with self.lock:
if self.fti:
self.fti.interrupt()
def removeDupsAndSort(matches: FullTextIndex.SearchResult) -> FullTextIndex.SearchResult:
"""Remove duplicates and sort"""
uniqueMatches = set()
for match in matches:
uniqueMatches.add(match)
matches = [match for match in uniqueMatches] # make list from set
matches.sort()
return matches
Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.