Reproog/novelWriter
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update tokenizer and html converter

Browse Source
This commit is contained in:
Veronica K. B. Olsen
2019-10-25 00:07:37 +02:00
parent a67d3ed599
commit 01dde7c8a4
2 changed files with 30 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nw/convert/tohtml.py
+7 -3
View File
@@ -28,9 +28,13 @@ class ToHtml(Tokenizer):
Tokenizer.doAutoReplace(self) Tokenizer.doAutoReplace(self)
repDict = { repDict = {
"<" : "&lt;", "<" : "&lt;",
">" : "&gt;", ">" : "&gt;",
"&" : "&amp;", "&" : "&amp;",
"\u2013" : "&endash;",
"\u2014" : "$emdash;",
"\u2500" : "$emdash;",
"\u2026" : "&hellip;",
} }
xRep = re.compile("|".join([re.escape(k) for k in repDict.keys()]), flags=re.DOTALL) 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) self.theText = xRep.sub(lambda x: repDict[x.group(0)], self.theText)
nw/convert/tokenizer.py
+23 -19
View File
@@ -26,27 +26,28 @@ logger = logging.getLogger(__name__)
class Tokenizer(): class Tokenizer():
FMT_B_B = 1 # Begin bold FMT_B_B = 1 # Begin bold
FMT_B_E = 2 # End bold FMT_B_E = 2 # End bold
FMT_I_B = 3 # Begin italics FMT_I_B = 3 # Begin italics
FMT_I_E = 4 # End italics FMT_I_E = 4 # End italics
FMT_U_B = 5 # Begin underline FMT_U_B = 5 # Begin underline
FMT_U_E = 6 # End underline FMT_U_E = 6 # End underline
T_EMPTY = 1 # Empty line (new paragraph) T_EMPTY = 1 # Empty line (new paragraph)
T_COMMENT = 2 # Comment line T_COMMENT = 2 # Comment line
T_COMMAND = 3 # Command line T_COMMAND = 3 # Command line
T_HEAD1 = 4 # Header 1 (title) T_HEAD1 = 4 # Header 1 (title)
T_HEAD2 = 5 # Header 2 (chapter) T_HEAD2 = 5 # Header 2 (chapter)
T_HEAD3 = 6 # Header 3 (scene) T_HEAD3 = 6 # Header 3 (scene)
T_HEAD4 = 7 # Header 4 T_HEAD4 = 7 # Header 4
T_TEXT = 8 # Text line T_TEXT = 8 # Text line
T_SEP = 9 # Scene separator T_SEP = 9 # Scene separator
T_PBREAK = 10 # Page break
A_LEFT = 1 # Left aligned A_LEFT = 1 # Left aligned
A_RIGHT = 2 # Right aligned A_RIGHT = 2 # Right aligned
A_CENTRE = 3 # Centred A_CENTRE = 3 # Centred
A_JUSTIFY = 4 # Justified A_JUSTIFY = 4 # Justified
def __init__(self, theProject, theParent): def __init__(self, theProject, theParent):
@@ -262,6 +263,7 @@ class Tokenizer():
self.theTokens[n] = (tType,tTemp,None,self.A_LEFT) self.theTokens[n] = (tType,tTemp,None,self.A_LEFT)
# For title page and partitions, we need to centre all text # For title page and partitions, we need to centre all text
# and for some formats, we need a page break
if isTitle or isPart: if isTitle or isPart:
for n in range(len(self.theTokens)): for n in range(len(self.theTokens)):
tToken = self.theTokens[n] tToken = self.theTokens[n]
@@ -270,6 +272,8 @@ class Tokenizer():
tFormat = tToken[2] tFormat = tToken[2]
self.theTokens[n] = (tType,tText,tFormat,self.A_CENTRE) self.theTokens[n] = (tType,tText,tFormat,self.A_CENTRE)
self.theTokens[n] = (self.T_PBREAK,"",None,self.A_LEFT)
return return
def doConvert(self): def doConvert(self):