def getExtracts(self, context, source):
"""
Link.getExtracts
context : (str)
source : (str)
Return a list of LinkInfo objects
"""
res = []
for textbetweenmarkers in TextBetweenMarkers.getExtracts(self, source):
name = textbetweenmarkers.substring
pos0 = textbetweenmarkers.pos0
separator = source.find(LINK_SEPARATOR)
if separator == -1:
# no separator, artiname only :
artiname = name
entryname = None
else:
# separator between artiname and entryname :
artiname = source[separator:]
entryname = source[:separator]
res.append( LinkInfo( context = context,
pos0 = pos0,
artiname = artiname,
entryname = entryname,
source = source ))
return res
def initFromStr(self,
informationsdata,
title_hlevel,
title_pending_text,
str_content,
reading_position,
srclanguage):
"""
Entry.initFromStr()
informationsdata : InformationsData object
title_hlevel : HierarchicalLevel object
title_pending_text : None or a string.
str_content : a list of strings.
reading_position : ReadingPosition object
"""
self.reset()
self.reading_position = reading_position
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# hierarchical level :
self.entrydata.hlevel = title_hlevel.hleveldata
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# title :
if title_pending_text is None:
self.entrydata.title = None
else:
# links are forbidden in the entries' title :
if LINK_START in title_pending_text:
msg = "(ERR059) Link found in an entry's title; title={0} -> {1}"
self.errors.error(msg.format(title_pending_text,
self.reading_position))
# to-be-duplicated entry ?
if BODY_ARTICLE_TO_DUPLICATED_NOTIMPORTANT in title_pending_text or \
BODY_ARTICLE_TO_DUPLICATED_IMPORTANT in title_pending_text:
if BODY_ARTICLE_TO_DUPLICATED_NOTIMPORTANT in title_pending_text:
# 'normal' symbol :
dup_symbol = BODY_ARTICLE_TO_DUPLICATED_NOTIMPORTANT
else:
# 'important' symbol :
dup_symbol = BODY_ARTICLE_TO_DUPLICATED_IMPORTANT
# only one result expected :
tbm = TextBetweenMarkers(marker_start=dup_symbol,
marker_end=dup_symbol)
results = tbm.getExtracts( title_pending_text )
if len(results) != 1:
msg = "(ERR058) Wrong format : " \
"the to-be-duplicated entry can't be read; -> {0}"
self.errors.error(msg.format(self.reading_position))
else:
self.entrydata.entry_to_be_duplicated = results[0].substring
self.entrydata.important_entry_to_be_dup = (dup_symbol == \
BODY_ARTICLE_TO_DUPLICATED_IMPORTANT)
# we erase the markers linked to the 'to-be-duplicated' entry :
title_pending_text = title_pending_text.replace(dup_symbol, "")
self.entrydata.title = title_pending_text.strip()
# links in <self.entrydata.title> ?
self.entrydata.links = Link().getExtracts(source = self.entrydata.title,
context = "entry.title+" + \
self.reading_position.getShortDescription())
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# text and extract(s) :
current_position = None # None or "extract"
current_extract = [] # list of strings
for line in str_content:
if line.strip() == "":
if current_position == "extract":
# end of the current extract :
new_extract = Extract( errors = self.errors,
logotherasdata = self.logotherasdata )
new_extract.initFromStr( informationsdata = informationsdata,
src = current_extract,
reading_position = reading_position,
srclanguage = srclanguage)
extract_freeness = \
informationsdata.getTheMinFreenessOfAnExtract(new_extract.extractdata)
if extract_freeness >= logotheras.options.OPTIONS["minimal freeness"]:
self.entrydata.append( new_extract.extractdata )
else:
msg = "skipping an extract due to its freeness value; extract={0}; -> {1}"
self.errors.info(msg.format(new_extract.extractdata, reading_position))
current_position = None
current_extract = []
elif not line.startswith(BODY_PREFIX_BEFORE_EXTRACT):
self.entrydata.text.append(line)
else:
if current_position is None:
# first line of an extract :
current_position = "extract"
current_extract.append( line[len(BODY_PREFIX_BEFORE_EXTRACT):] )
else:
# next line of the current extract :
current_extract.append( line[len(BODY_PREFIX_BEFORE_EXTRACT):] )
if current_position is not None:
# we add the last extract :
new_extract = Extract( errors = self.errors,
logotherasdata = self.logotherasdata )
new_extract.initFromStr( informationsdata = informationsdata,
src = current_extract,
reading_position = reading_position,
srclanguage = srclanguage)
extract_freeness = \
informationsdata.getTheMinFreenessOfAnExtract(new_extract.extractdata)
if extract_freeness >= logotheras.options.OPTIONS["minimal freeness"]:
self.entrydata.append( new_extract.extractdata )
else:
msg = "skipping an extract due to its freeness value; extract={0}; -> {1}"
self.errors.info(msg.format(new_extract.extractdata, reading_position))
return self