Cleaned up the nw/convert folder a bit
This commit is contained in:
Veronica K. B. Olsen
@@ -0,0 +1,104 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
"""novelWriter HTML Text Converter
|
||||
|
||||
novelWriter – HTML Text Converter
|
||||
===================================
|
||||
Extends the Tokenizer class to write HTML
|
||||
|
||||
File History:
|
||||
Created: 2019-05-07 [0.0.1]
|
||||
|
||||
"""
|
||||
|
||||
import logging
|
||||
import re
|
||||
import nw
|
||||
|
||||
from nw.convert.tokenizer import Tokenizer
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
class ToHtml(Tokenizer):
|
||||
|
||||
def __init__(self, theProject, theParent):
|
||||
Tokenizer.__init__(self, theProject, theParent)
|
||||
return
|
||||
|
||||
def doAutoReplace(self):
|
||||
Tokenizer.doAutoReplace(self)
|
||||
|
||||
repDict = {
|
||||
"<" : "<",
|
||||
">" : ">",
|
||||
"&" : "&",
|
||||
"\u2013" : "&endash;",
|
||||
"\u2014" : "$emdash;",
|
||||
"\u2500" : "$emdash;",
|
||||
"\u2026" : "…",
|
||||
}
|
||||
xRep = re.compile("|".join([re.escape(k) for k in repDict.keys()]), flags=re.DOTALL)
|
||||
self.theText = xRep.sub(lambda x: repDict[x.group(0)], self.theText)
|
||||
|
||||
return
|
||||
|
||||
def doConvert(self):
|
||||
|
||||
htmlTags = {
|
||||
self.FMT_B_B : "<strong>",
|
||||
self.FMT_B_E : "</strong>",
|
||||
self.FMT_I_B : "<em>",
|
||||
self.FMT_I_E : "</em>",
|
||||
self.FMT_U_B : "<u>",
|
||||
self.FMT_U_E : "</u>",
|
||||
}
|
||||
|
||||
self.theResult = ""
|
||||
thisPar = []
|
||||
for tType, tText, tFormat, tAlign in self.theTokens:
|
||||
|
||||
aStyle = []
|
||||
if tAlign == self.A_CENTRE:
|
||||
aStyle.append("text-align: center;")
|
||||
|
||||
if len(aStyle) > 0:
|
||||
hStyle = " style='%s'" % (" ".join(aStyle))
|
||||
else:
|
||||
hStyle = ""
|
||||
|
||||
if tType == self.T_EMPTY:
|
||||
if len(thisPar) > 0:
|
||||
self.theResult += "<p%s>%s</p>\n" % (hStyle," ".join(thisPar))
|
||||
thisPar = []
|
||||
|
||||
elif tType == self.T_HEAD1:
|
||||
self.theResult += "<h1%s>%s</h1>\n" % (hStyle,tText)
|
||||
|
||||
elif tType == self.T_HEAD2:
|
||||
self.theResult += "<h2%s>%s</h2>\n" % (hStyle,tText)
|
||||
|
||||
elif tType == self.T_HEAD3:
|
||||
self.theResult += "<h3%s>%s</h3>\n" % (hStyle,tText)
|
||||
|
||||
elif tType == self.T_HEAD4:
|
||||
self.theResult += "<h4%s>%s</h4>\n" % (hStyle,tText)
|
||||
|
||||
elif tType == self.T_SEP:
|
||||
self.theResult += "<div%s>%s</div>\n" % (hStyle,tText)
|
||||
|
||||
elif tType == self.T_TEXT:
|
||||
tTemp = tText
|
||||
for xPos, xLen, xFmt in reversed(tFormat):
|
||||
tTemp = tTemp[:xPos]+htmlTags[xFmt]+tTemp[xPos+xLen:]
|
||||
thisPar.append(tTemp)
|
||||
|
||||
elif tType == self.T_COMMENT and self.doComments:
|
||||
self.theResult += "<pre>%s</pre>\n" % tText
|
||||
|
||||
elif tType == self.T_COMMAND and self.doCommands:
|
||||
self.theResult += "<pre>%s</pre>\n" % tText
|
||||
|
||||
# print(self.theResult)
|
||||
|
||||
return
|
||||
|
||||
# END Class ToHtml
|
||||
@@ -0,0 +1,155 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
"""novelWriter LaTeX Converter
|
||||
|
||||
novelWriter – LaTeX Converter
|
||||
===============================
|
||||
Extends the Tokenizer class to write LaTeX
|
||||
|
||||
File History:
|
||||
Created: 2019-10-24 [0.3.1]
|
||||
|
||||
"""
|
||||
|
||||
import textwrap
|
||||
import logging
|
||||
import re
|
||||
import nw
|
||||
|
||||
from nw.convert.tokenizer import Tokenizer
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
class ToLaTeX(Tokenizer):
|
||||
|
||||
def __init__(self, theProject, theParent):
|
||||
Tokenizer.__init__(self, theProject, theParent)
|
||||
return
|
||||
|
||||
def doAutoReplace(self):
|
||||
Tokenizer.doAutoReplace(self)
|
||||
|
||||
repDict = {
|
||||
"\u2013" : "--",
|
||||
"\u2014" : "---",
|
||||
"\u2500" : "---",
|
||||
"\u2026" : "...",
|
||||
}
|
||||
xRep = re.compile("|".join([re.escape(k) for k in repDict.keys()]), flags=re.DOTALL)
|
||||
self.theText = xRep.sub(lambda x: repDict[x.group(0)], self.theText)
|
||||
|
||||
return
|
||||
|
||||
def doConvert(self):
|
||||
|
||||
texTags = {
|
||||
self.FMT_B_B : r"\textbf{",
|
||||
self.FMT_B_E : r"}",
|
||||
self.FMT_I_B : r"\textit{",
|
||||
self.FMT_I_E : r"}",
|
||||
self.FMT_U_B : r"\underline{",
|
||||
self.FMT_U_E : r"}",
|
||||
}
|
||||
|
||||
if self.wordWrap > 0:
|
||||
tWrap = textwrap.TextWrapper(
|
||||
width = self.wordWrap,
|
||||
initial_indent = "",
|
||||
subsequent_indent = "",
|
||||
expand_tabs = True,
|
||||
replace_whitespace = True,
|
||||
fix_sentence_endings = False,
|
||||
break_long_words = True,
|
||||
drop_whitespace = True,
|
||||
break_on_hyphens = True,
|
||||
tabsize = 8,
|
||||
max_lines = None
|
||||
)
|
||||
tComm = textwrap.TextWrapper(
|
||||
width = self.wordWrap-2,
|
||||
initial_indent = "",
|
||||
subsequent_indent = "",
|
||||
expand_tabs = True,
|
||||
replace_whitespace = True,
|
||||
fix_sentence_endings = False,
|
||||
break_long_words = True,
|
||||
drop_whitespace = True,
|
||||
break_on_hyphens = True,
|
||||
tabsize = 8,
|
||||
max_lines = None
|
||||
)
|
||||
|
||||
self.theResult = ""
|
||||
thisPar = []
|
||||
for tType, tText, tFormat, tAlign in self.theTokens:
|
||||
|
||||
begText = ""
|
||||
endText = "\n"
|
||||
if tAlign == self.A_CENTRE:
|
||||
begText = "\\begin{center}\n"
|
||||
endText = "\\end{center}\n\n"
|
||||
|
||||
# First check if we have a comment or plain text, as they need some
|
||||
# extra replacing before we proceed to wrapping and final formatting.
|
||||
if tType == self.T_COMMENT:
|
||||
tText = "%% %s" % tText
|
||||
|
||||
elif tType == self.T_TEXT:
|
||||
tTemp = tText
|
||||
for xPos, xLen, xFmt in reversed(tFormat):
|
||||
tTemp = tTemp[:xPos]+texTags[xFmt]+tTemp[xPos+xLen:]
|
||||
tText = tTemp
|
||||
|
||||
tLen = len(tText)
|
||||
|
||||
# The text can now be word wrapped, if we have requested this and it's needed.
|
||||
if self.wordWrap > 0 and tLen > self.wordWrap:
|
||||
if tType == self.T_COMMENT:
|
||||
aText = tComm.wrap(tText)
|
||||
tText = "\n% ".join(aText)
|
||||
else:
|
||||
tText = tWrap.fill(tText)
|
||||
|
||||
# Then the text can receive final formatting before we append it to the results.
|
||||
# We also store text lines in a buffer and merge them only when we find an empty line,
|
||||
# indicating a new paragraph.
|
||||
if tType == self.T_EMPTY:
|
||||
if len(thisPar) > 0:
|
||||
self.theResult += begText
|
||||
self.theResult += "%s\n" % tWrap.fill(" ".join(thisPar))
|
||||
self.theResult += endText
|
||||
thisPar = []
|
||||
|
||||
elif tType == self.T_HEAD1:
|
||||
self.theResult += begText
|
||||
self.theResult += "{\\Huge %s}\n" % tText
|
||||
self.theResult += endText
|
||||
|
||||
elif tType == self.T_HEAD2:
|
||||
self.theResult += "\\chapter*{%s}\n\n" % tText
|
||||
|
||||
elif tType == self.T_HEAD3:
|
||||
self.theResult += "\\section*{%s}\n\n" % tText
|
||||
|
||||
elif tType == self.T_HEAD4:
|
||||
self.theResult += "\\subsection*{%s}\n\n" % tText
|
||||
|
||||
elif tType == self.T_SEP:
|
||||
self.theResult += begText
|
||||
self.theResult += "%s\n" % tText
|
||||
self.theResult += endText
|
||||
|
||||
elif tType == self.T_TEXT:
|
||||
thisPar.append(tText)
|
||||
|
||||
elif tType == self.T_PBREAK:
|
||||
self.theResult += "\\newpage\n\n"
|
||||
|
||||
elif tType == self.T_COMMENT and self.doComments:
|
||||
self.theResult += "%s\n\n" % tText
|
||||
|
||||
elif tType == self.T_COMMAND and self.doCommands:
|
||||
self.theResult += "%% @%s\n\n" % tText
|
||||
|
||||
return
|
||||
|
||||
# END Class ToLaTeX
|
||||
@@ -0,0 +1,112 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
"""novelWriter Markdown Text Converter
|
||||
|
||||
novelWriter – Markdown Text Converter
|
||||
=======================================
|
||||
Extends the Tokenizer class to write Markdown
|
||||
|
||||
File History:
|
||||
Created: 2019-10-19 [0.3]
|
||||
|
||||
"""
|
||||
|
||||
import textwrap
|
||||
import logging
|
||||
import re
|
||||
import nw
|
||||
|
||||
from nw.convert.tokenizer import Tokenizer
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
class ToMarkdown(Tokenizer):
|
||||
|
||||
def __init__(self, theProject, theParent):
|
||||
Tokenizer.__init__(self, theProject, theParent)
|
||||
return
|
||||
|
||||
def doConvert(self):
|
||||
|
||||
mdTags = {
|
||||
self.FMT_B_B : "**",
|
||||
self.FMT_B_E : "**",
|
||||
self.FMT_I_B : "_",
|
||||
self.FMT_I_E : "_",
|
||||
self.FMT_U_B : "__",
|
||||
self.FMT_U_E : "__",
|
||||
}
|
||||
|
||||
if self.wordWrap > 0:
|
||||
tWrap = textwrap.TextWrapper(
|
||||
width = self.wordWrap,
|
||||
initial_indent = "",
|
||||
subsequent_indent = "",
|
||||
expand_tabs = True,
|
||||
replace_whitespace = True,
|
||||
fix_sentence_endings = False,
|
||||
break_long_words = True,
|
||||
drop_whitespace = True,
|
||||
break_on_hyphens = True,
|
||||
tabsize = 8,
|
||||
max_lines = None
|
||||
)
|
||||
|
||||
self.theResult = ""
|
||||
thisPar = []
|
||||
for tType, tText, tFormat, tAlign in self.theTokens:
|
||||
|
||||
# First check if we have a comment or plain text, as they need some
|
||||
# extra replacing before we proceed to wrapping and final formatting.
|
||||
if tType == self.T_COMMENT:
|
||||
tText = " %s" % tText
|
||||
|
||||
elif tType == self.T_TEXT:
|
||||
tTemp = tText
|
||||
for xPos, xLen, xFmt in reversed(tFormat):
|
||||
tTemp = tTemp[:xPos]+mdTags[xFmt]+tTemp[xPos+xLen:]
|
||||
tText = tTemp
|
||||
|
||||
tLen = len(tText)
|
||||
|
||||
# The text can now be word wrapped, if we have requested this and it's needed.
|
||||
if self.wordWrap > 0 and tLen > self.wordWrap:
|
||||
if tType == self.T_COMMENT:
|
||||
tText = textwrap.fill(tText.strip(),initial_indent=" ",subsequent_indent=" ")
|
||||
else:
|
||||
tText = tWrap.fill(tText)
|
||||
|
||||
# Then the text can receive final formatting before we append it to the results.
|
||||
# We also store text lines in a buffer and merge them only when we find an empty line,
|
||||
# indicating a new paragraph.
|
||||
if tType == self.T_EMPTY:
|
||||
if len(thisPar) > 0:
|
||||
self.theResult += "%s\n\n" % " ".join(thisPar)
|
||||
thisPar = []
|
||||
|
||||
elif tType == self.T_HEAD1:
|
||||
self.theResult += "# %s\n\n" % tText
|
||||
|
||||
elif tType == self.T_HEAD2:
|
||||
self.theResult += "## %s\n\n" % tText
|
||||
|
||||
elif tType == self.T_HEAD3:
|
||||
self.theResult += "### %s\n\n" % tText
|
||||
|
||||
elif tType == self.T_HEAD4:
|
||||
self.theResult += "#### %s\n\n" % tText
|
||||
|
||||
elif tType == self.T_SEP:
|
||||
self.theResult += "%s\n\n" % tText
|
||||
|
||||
elif tType == self.T_TEXT:
|
||||
thisPar.append(tText)
|
||||
|
||||
elif tType == self.T_COMMENT and self.doComments:
|
||||
self.theResult += "%s\n\n" % tText
|
||||
|
||||
elif tType == self.T_COMMAND and self.doCommands:
|
||||
self.theResult += "%s\n\n" % tText
|
||||
|
||||
return
|
||||
|
||||
# END Class ToMarkdown
|
||||
@@ -0,0 +1,119 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
"""novelWriter Plain Text Converter
|
||||
|
||||
novelWriter – Plain Text Converter
|
||||
====================================
|
||||
Extends the Tokenizer class to convert to plain text
|
||||
|
||||
File History:
|
||||
Created: 2019-10-26 [0.3.1]
|
||||
|
||||
"""
|
||||
|
||||
import textwrap
|
||||
import logging
|
||||
import re
|
||||
import nw
|
||||
|
||||
from nw.convert.tokenizer import Tokenizer
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
class ToText(Tokenizer):
|
||||
|
||||
def __init__(self, theProject, theParent):
|
||||
Tokenizer.__init__(self, theProject, theParent)
|
||||
return
|
||||
|
||||
def doConvert(self):
|
||||
"""Converts the tokenized text into plain text.
|
||||
"""
|
||||
|
||||
if self.wordWrap > 0:
|
||||
tWrap = textwrap.TextWrapper(
|
||||
width = self.wordWrap,
|
||||
initial_indent = "",
|
||||
subsequent_indent = "",
|
||||
expand_tabs = True,
|
||||
replace_whitespace = True,
|
||||
fix_sentence_endings = False,
|
||||
break_long_words = True,
|
||||
drop_whitespace = True,
|
||||
break_on_hyphens = True,
|
||||
tabsize = 8,
|
||||
max_lines = None
|
||||
)
|
||||
|
||||
self.theResult = ""
|
||||
thisPar = []
|
||||
for tType, tText, tFormat, tAlign in self.theTokens:
|
||||
|
||||
# First check if we have a comment or plain text, as they need some
|
||||
# extra replacing before we proceed to wrapping and final formatting.
|
||||
if tType == self.T_COMMENT:
|
||||
tText = "[%s]" % tText
|
||||
|
||||
elif tType == self.T_TEXT:
|
||||
tTemp = tText
|
||||
for xPos, xLen, xFmt in reversed(tFormat):
|
||||
tTemp = tTemp[:xPos]+tTemp[xPos+xLen:]
|
||||
tText = tTemp
|
||||
|
||||
tLen = len(tText)
|
||||
|
||||
# The text can now be word wrapped, if we have requested this and it's needed.
|
||||
if tAlign == self.A_CENTRE:
|
||||
if self.wordWrap > 0:
|
||||
if tLen > self.wordWrap:
|
||||
aText = tWrap.wrap(tText)
|
||||
for n in range(len(aText)):
|
||||
aText[n] = self._centreText(aText[n],self.wordWrap)
|
||||
tText = "\n".join(aText)
|
||||
else:
|
||||
tText = self._centreText(tText,self.wordWrap)
|
||||
else:
|
||||
if self.wordWrap > 0 and tLen > self.wordWrap:
|
||||
tText = tWrap.fill(tText)
|
||||
|
||||
# Then the text can receive final formatting before we append it to the results.
|
||||
# We also store text lines in a buffer and merge them only when we find an empty line,
|
||||
# indicating a new paragraph.
|
||||
if tType == self.T_EMPTY:
|
||||
if len(thisPar) > 0:
|
||||
self.theResult += "%s\n\n" % " ".join(thisPar)
|
||||
thisPar = []
|
||||
|
||||
elif tType == self.T_HEAD1:
|
||||
uLine = "="*min(tLen,self.wordWrap)
|
||||
if tAlign == self.A_CENTRE:
|
||||
uLine = self._centreText(uLine,self.wordWrap)
|
||||
self.theResult += "%s\n%s\n\n" % (tText,uLine)
|
||||
|
||||
elif tType == self.T_HEAD2:
|
||||
uLine = "~"*min(tLen,self.wordWrap)
|
||||
self.theResult += "%s\n%s\n\n" % (tText,uLine)
|
||||
|
||||
elif tType == self.T_HEAD3:
|
||||
uLine = "-"*min(tLen,self.wordWrap)
|
||||
self.theResult += "%s\n%s\n\n" % (tText,uLine)
|
||||
|
||||
elif tType == self.T_HEAD4:
|
||||
self.theResult += "%s\n\n" % tText
|
||||
|
||||
elif tType == self.T_SEP:
|
||||
if self.wordWrap > 0 and tLen < self.wordWrap:
|
||||
tText = self._centreText(tText,self.wordWrap)
|
||||
self.theResult += "%s\n\n" % tText
|
||||
|
||||
elif tType == self.T_TEXT:
|
||||
thisPar.append(tText)
|
||||
|
||||
elif tType == self.T_COMMENT and self.doComments:
|
||||
self.theResult += "%s\n\n" % tText
|
||||
|
||||
elif tType == self.T_COMMAND and self.doCommands:
|
||||
self.theResult += "%s\n\n" % tText
|
||||
|
||||
return
|
||||
|
||||
# END Class ToText
|
||||
Reference in New Issue
Block a user