def do_action(options):
"""Act upon the indicated type"""
finput = options['input']
foutput = options['output']
fcompare = options['compare']
action = options['action']
oerr = util.ErrHandle()
result = None
if action == "simple":
result = Sfm.filter(finput, foutput, "simple")
elif action == "compare":
result = Sfm.compare(finput, fcompare, foutput)
# Return the result
return result
def filter(finput, foutput, ftype):
"""Filter according to the indicated filter type"""
oerr = util.ErrHandle()
try:
# r_sfm = re.compile(r"\\\w+[\s\*]")
r_sfm = re.compile(r"\\\w+((\s)|(\*)|$)")
# Read the input
sfmfile = SfmFile(oerr)
result = sfmfile.read(finput)
if result:
# Filter the input according to filter type
lst_c = []
for one_c in sfmfile.chapters:
verses = []
for one_v in one_c:
# Perform the filtering
if ftype == "none":
new_v = one_v
elif ftype == "simple":
# Perform simple filtering
new_v = r_sfm.sub("", one_v)
# Replace quotation marks
new_v = new_v.replace("«", "<<")
new_v = new_v.replace("»", ">>")
# Remove *g**
new_v = new_v.replace("*g**", "")
verses.append(new_v)
# Process the verses
lst_c.append(verses)
# Write the new list as a file
result = sfmfile.write(foutput, lst_c)
except:
msg = oerr.get_error_message()
oerr.DoError("filter")
result = False
return result
"""
The classes in this models.py are used by the Python application hebot
"""
import os, sys
import copy
import json
import util
cat_dict = {}
cat_dict['CP-Conj']='ConjP'
errHandle = util.ErrHandle()
def get_error_message():
arInfo = sys.exc_info()
if len(arInfo) == 3:
sMsg = str(arInfo[1])
if arInfo[2] != None:
sMsg += " at line " + str(arInfo[2].tb_lineno)
return sMsg
else:
return ""
class HierObj(object):
"""Hierarchical object"""
pos = "" # Grammatical category
txt = "" # The text associated with this instance
class convert(object):
"""split texts"""
errHandle = util.ErrHandle()
folder = ""
def __init__(self, **kwargs):
# No real action here
return super().__init__(**kwargs)
def split2texts(self, options):
"""Split one large text into several smaller"""
try:
# Get the input file
sInput = options['input']
sOutput = options['output']
self.folder = sOutput
sHeader = "" # Name of text
lText = [] # Lines for a text
# Open the input
fInput = open(sInput, 'r', encoding='UTF8')
# Walk through all the input lines
for line in fInput.readlines():
# Check if this identifies the start of a text: ( ICLE-
if line.startswith("( ICLE-") or line.startswith("(ICLE-"):
# Need to chop off the part until the first right bracket
iPos = line.find(")")
if iPos >= 0:
self.writetext(sHeader, lText)
# Okay, this is the beginning of a text
sHeader = line[2:iPos - 1].replace(" ", "")
line = line[iPos + 1:].strip()
# Add the line to the text
lText.append(line)
# After finishing: output the final text
self.writetext(sHeader, lText)
return True
except:
sMsg = self.errHandle.get_error_message()
return False
def writetext(self, sHeader, lText):
try:
# If existing, finish and save a previous text
if sHeader != "":
# Save current text
sFile = self.folder + "/" + sHeader + ".txt"
fOutput = open(sFile, 'w', encoding='UTF8')
fOutput.writelines(lText)
#for line_out in lText:
# line_out = line_out.replace("\n", "")
# line_out = line_out.replace("\r", "")
# fOutput.write(line_out + "\n")
fOutput.close()
lText.clear()
return True
except:
sMsg = self.errHandle.get_error_message()
return False
def compare(finput, fcompare, foutput):
"""Compare two SFM files and return the result"""
oerr = util.ErrHandle()
def pre_process(sInput):
sOutput = re.sub(r'\s\-+\s', " ", sInput)
sOutput = sOutput.replace(u'\u0406', '\u04c0')
sOutput = sOutput.replace("„", "<")
sOutput = sOutput.replace('“', ">")
sOutput = sOutput.replace('–', "")
sOutput = sOutput.replace(".", "")
sOutput = sOutput.replace(",", "")
sOutput = sOutput.lower()
return sOutput
try:
# Read both files
sfminput = SfmFile(oerr)
sfmcompare = SfmFile(oerr)
bInput = sfminput.read(finput)
bCompare = sfmcompare.read(fcompare)
oInput = sfminput.chapters
oCompare = sfmcompare.chapters
lst_diff = []
# Compare chapters
for idx_c, ch_input in enumerate(oInput):
# Get the corresponding comparison chapter
ch_compare = oCompare[idx_c]
# Compare verses
for idx_v, vs_input in enumerate(ch_input):
vs_compare = ch_compare[idx_v]
# A bit more pre-processing on the verse contents
vs_input = pre_process(vs_input)
vs_compare = pre_process(vs_compare)
# Convert both verses into arrays
w_input = re.split(r'\s+', vs_input)
w_compare = re.split(r'\s+', vs_compare)
length = min(len(w_input), len(w_compare))
for idx in range(length):
if w_input[idx] != w_compare[idx]:
# Found the first difference
msg = "{}:{} at word #{} [{}] versus [{}]".format(
idx_c, idx_v, idx, w_input[idx],
w_compare[idx])
lst_diff.append(msg)
break
# Combine the comparison
sText = "\n".join(lst_diff)
# Write as output
with open(foutput, "w", encoding="utf-8") as f:
f.write(sText)
result = True
except:
msg = oerr.get_error_message()
oerr.DoError("compare")
result = False
return result
