Veronica K. B. Olsen
119 lines
3.6 KiB
Python
119 lines
3.6 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""
|
||
novelWriter – Various Tools
|
||
===========================
|
||
Various core tool functions
|
||
|
||
File History:
|
||
Created: 2019-04-22 [0.0.1] countWords
|
||
Created: 2020-07-05 [0.10.0] numberToRoman
|
||
|
||
This file is a part of novelWriter
|
||
Copyright 2018–2021, Veronica Berglyd Olsen
|
||
|
||
This program is free software: you can redistribute it and/or modify
|
||
it under the terms of the GNU 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
|
||
General Public License for more details.
|
||
|
||
You should have received a copy of the GNU General Public License
|
||
along with this program. If not, see <https://www.gnu.org/licenses/>.
|
||
"""
|
||
|
||
import logging
|
||
|
||
from nw.constants import nwUnicode
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
# =============================================================================================== #
|
||
# Simple Word Counter
|
||
# =============================================================================================== #
|
||
|
||
def countWords(theText):
|
||
"""Count words in a piece of text, skipping special syntax and
|
||
comments.
|
||
"""
|
||
charCount = 0
|
||
wordCount = 0
|
||
paraCount = 0
|
||
prevEmpty = True
|
||
|
||
# We need to treat dashes as word separators for counting words.
|
||
# The check+replace apprach is much faster that direct replace for
|
||
# large texts, and a bit slower for small texts, but in the latter
|
||
# case it doesn't matter.
|
||
if nwUnicode.U_ENDASH in theText:
|
||
theText = theText.replace(nwUnicode.U_ENDASH, " ")
|
||
if nwUnicode.U_EMDASH in theText:
|
||
theText = theText.replace(nwUnicode.U_EMDASH, " ")
|
||
|
||
for aLine in theText.splitlines():
|
||
|
||
countPara = True
|
||
theLen = len(aLine)
|
||
|
||
if theLen == 0:
|
||
prevEmpty = True
|
||
continue
|
||
if aLine[0] == "@" or aLine[0] == "%":
|
||
continue
|
||
|
||
if aLine[0:5] == "#### ":
|
||
wordCount -= 1
|
||
charCount -= 5
|
||
countPara = False
|
||
elif aLine[0:4] == "### ":
|
||
wordCount -= 1
|
||
charCount -= 4
|
||
countPara = False
|
||
elif aLine[0:3] == "## ":
|
||
wordCount -= 1
|
||
charCount -= 3
|
||
countPara = False
|
||
elif aLine[0:2] == "# ":
|
||
wordCount -= 1
|
||
charCount -= 2
|
||
countPara = False
|
||
|
||
wordCount += len(aLine.split())
|
||
charCount += theLen
|
||
if countPara and prevEmpty:
|
||
paraCount += 1
|
||
|
||
prevEmpty = not countPara
|
||
|
||
return charCount, wordCount, paraCount
|
||
|
||
# =============================================================================================== #
|
||
# Convert an Integer to a Roman Number
|
||
# =============================================================================================== #
|
||
|
||
def numberToRoman(numVal, isLower=False):
|
||
"""Convert an integer to a roman number.
|
||
"""
|
||
if not isinstance(numVal, int):
|
||
return "NAN"
|
||
if numVal < 1 or numVal > 4999:
|
||
return "OOR"
|
||
|
||
theValues = [
|
||
(1000, "M"), (900, "CM"), (500, "D"), (400, "CD"), (100, "C"), (90, "XC"),
|
||
(50, "L"), (40, "XL"), (10, "X"), (9, "IX"), (5, "V"), (4, "IV"), (1, "I"),
|
||
]
|
||
|
||
romNum = ""
|
||
for theDiv, theSym in theValues:
|
||
n = numVal//theDiv
|
||
romNum += n*theSym
|
||
numVal -= n*theDiv
|
||
if numVal <= 0:
|
||
break
|
||
|
||
return romNum.lower() if isLower else romNum
|