示例#1
0
def read_token_simplify_file(level):
    fname = os.path.join(idatapath, 'token_simplify_%s.txt' % level)
    fname = fileabspath.filePathAdj().get_file_path(fname)
    #lines = open(fname, 'r').readlines()
    lines = read_idata(fname)

    d_dict = {}
    for line in lines:
        line_sp = line.split('\t')
        d_dict[line_sp[0].strip()] = line_sp[1].strip()
    return d_dict
示例#2
0
def get_level_igs(level):
    level_igs = []
    fname = os.path.join(idatapath, 'token_controller_%s.txt' % level)
    fname = fileabspath.filePathAdj().get_file_path(fname)
    #lines = open(fname, 'r').readlines()
    lines = read_idata(fname)
    if not lines: return level_igs
    for line in lines[1:]:
        line = line.strip('\n')
        ls = line.split('\t')
        if ls[3].strip() == 'None': continue
        if 1:  #str(level) == ls[0].strip():
            level_igs.append(ls[1:])
    return level_igs
示例#3
0
def get_level_igs_user(level, user):
    level_igs = []
    conf_path = cfgObj.get_config('PageAnalysis', 'rule_file_path')
    fname = os.path.join(conf_path, user, 'token_controller_%s.txt' % level)
    #fname = os.path.join(idatapath, 'token_controller_%s.txt' %level)
    fname = fileabspath.filePathAdj().get_file_path(fname)
    #lines = open(fname, 'r').readlines()
    lines = read_idata(fname)
    if not lines: return level_igs
    for line in lines[1:]:
        line = line.strip('\n')
        ls = line.split('\t')
        if ls[3].strip() == 'None': continue
        if 1:  #str(level) == ls[0].strip():
            level_igs.append(ls[1:])
    return level_igs
示例#4
0
def read_rule_selection_file(level):
    fname = os.path.join(idatapath, 'rule_igs_%s.txt' % level)
    fname = fileabspath.filePathAdj().get_file_path(fname)
    #lines = open(fname, 'r').readlines()
    lines = read_idata(fname)

    d_dict = {}
    for line in lines:
        if not line.strip(): continue
        lsp = line.strip('\n').split('\t')
        d_dict[lsp[0].strip()] = []
        for l in lsp[1:]:
            if not l.strip(): continue
            d_dict[lsp[0].strip()].append(l.strip())

    return d_dict
import os, sys
import shelve

import common.baseobj as bobj
import common.getconfig as getconfig
import common.datastore as datastore
import common.get_doc_data as get_doc_data
import common.filePathAdj as fileabspath
import common.decfile as decfile

#cfgfname = fileabspath.filePathAdj().get_file_path('/var/www/cgi-bin/tasinfosieveresearch/tirsrc2/tirintf2/modules/PDF_APP/config.ini')
#cfgfname = fileabspath.filePathAdj().get_file_path('/var/www/cgi-bin/tasfundamentals/tfmsrc/tfmintf2/config_fundamentals.ini')
cfgfname = fileabspath.filePathAdj().get_file_path(
    '/var/www/cgi-bin/tasfundamentals/tfmsrc/tfmsrcpdf/src/config.ini')
cfgObj = getconfig.getconfig(cfgfname)


#idatapath = cfgObj.get_config('PageAnalysis', 'input')
#ipath, self.opath, self.isdb, self.isenc = bobj.BaseObj().get_project_info()
#self.isdb = int(self.isdb)
#self.isenc = int(self.isenc)
#ipath = '/var/www/html/INFOSIEVE_PROJECTS/AssetsDemo/data/output/'
#self.opath = '/var/www/html/INFOSIEVE_PROJECTS/AssetsDemo/data/output/'
#self.isdb = 1
#self.isenc = 1
class common_func:
    def __init__(self, ipath, opath, isdb, isenc):
        self.ipath = ipath
        self.opath = opath
        self.isdb = isdb
        self.isenc = isenc