def title_and_summary(self):
"""
Return the first block's content as title, if it is a paragraph or
comment, then the second block's content as a summary, if it is a
caption. Content will be trimmed with an ellipsis added, as one line.
"""
title, summary = '', ''
if len(self.blocks) > 0:
if isinstance(self.blocks[0], Paragraph):
title = one_line(
shorten(self.blocks[0].content, 128, placeholder="..."))
if isinstance(self.blocks[0], CharacterBlock):
if self.blocks[0].control_character == '%':
title = one_line(
shorten(self.blocks[0].content[2:],
128,
placeholder="..."))
if len(self.blocks) > 1:
if isinstance(self.blocks[1], CharacterBlock):
if self.blocks[1].control_character == Config.caption:
summary = one_line(
shorten(self.blocks[1].content[2:],
128,
placeholder="..."))
return title, summary
def split_to_array(text, prefixes, capture_characters=True):
"""
? This
/ is
?
/ a block
Note line 3 is 1 char in length; must match a space OR a line ending.
For prefixes = '?/=':
With capture_characters:
[('?', 'This'), ('/', 'is'), ('?', ''), ('/', 'a block')]
Without:
['This', 'is', '', 'a block']
"""
# Retain the first prefix if present
r1 = re.compile("[%s](?: ?|$)" % re.escape(prefixes))
if r1.match(text): # at start of string, vs. search()
prefix, content = [text[0]], text[2:]
else:
prefix, content = [prefixes[0]], text
if capture_characters:
# Split with brackets captures the leading chars...
r2 = re.compile("\n([%s])(?: ?|$)" % re.escape(prefixes))
lines = [one_line(_) for _ in r2.split(content)]
l = prefix + lines # So: char, line, char, line...
# Convert to [(char, line), (char, line)... ]
out = [tuple(l[i:i + 2]) for i in range(0, len(l), 2)]
else:
r2 = re.compile("\n[%s](?: ?|$)" % re.escape(prefixes))
out = [one_line(_) for _ in r2.split(content)]
return out
def tag(self, alias1, tag1, subtag1, punctuation, numbering, count):
"""
Take #Tags:Tag and return a link to its Index line.
Also store the back-link for when the index is generated.
"""
alias = one_line(alias1)
tag = one_line(tag1)
subtag = one_line(subtag1)
number = get_number(numbering)
nav_id = get_nav_id(tag, subtag, numbering, count)
if tag not in self.tags:
self.tags[tag] = {}
if subtag not in self.tags[tag]:
self.tags[tag][subtag] = {}
if number not in self.tags[tag][subtag]:
self.tags[tag][subtag][number] = []
link = trim("""
<a id=\"%s\" href=\"#ref_%s\">%s%s<sup>%s</sup></a>
""") % (
nav_id, nav_id, alias, punctuation, count
)
ref_link = "<a id=\"ref_%s\" href=\"#%s\">%s</a>" % \
(nav_id, nav_id, count)
self.tags[tag][subtag][number] += [ref_link]
return link
def text(self):
"""
Leave lines beginning with a control character unwrapped.
"""
tuples = split_to_array(self.content, Config.all_control_chars)
lines = [char + ' ' + one_line(line) for char, line in tuples]
space_above = "\n" if self.control_character in Config.subheads else ""
return space_above + "\n".join(lines)
def test_one_line():
text = trim("""
Sentence. Sentence!
Sentence; sentence. Sentence
sentence.
""")
normalised = "Sentence. Sentence! Sentence; sentence. Sentence sentence."
assert one_line(text) == normalised
def split_to_dictionary(text, prefix='$', delimiter='='):
"""
Like split_to_array, but with leaders that become keys.
$ key1 = value1
$ key2 = value2
{'key1': 'value1',
'key2': 'value2'}
"""
lines = split_to_array(text, prefix, capture_characters=True)
out = {}
for char, tail in lines:
parts = tail.split(' %s ' % delimiter)
if len(parts) == 2:
out[parts[0].strip()] = one_line(parts[1].strip())
return out
def __init__(self, text: str):
"Normalize spacing."
self.content = one_line(text)
def extract_title(text):
"""
Return the first paragraph in a block of text.
"""
return one_line(text.split("\n\n", 1)[0])