oly
/
eorg
mirror of https://gitlab.com/python-open-source-library-collection/eorg.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Added secondary image scanning test.

This commit is contained in:
Oliver Marks 2018-11-26 07:17:59 +00:00
parent 483606e95b
commit ac899b8ada
3 changed files with 68 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

77
eorg/parser.py
View File

@ -18,7 +18,9 @@ class Document:
if not idx:
if default is not None:
return default
raise AttributeError(f"Attribute of {name} does not exist in document")
raise AttributeError(
f"Attribute of {name} does not exist in document"
)
if len(idx) == 1:
return self.doc[idx[0]].value
return [self.doc[v].value for v in idx]
@ -40,9 +42,9 @@ class Document:
def previous(self, match):
if self.pos is 0:
return None
if self.doc[self.pos-1].token != match:
if self.doc[self.pos - 1].token != match:
return None
return self.doc[self.pos-1]
return self.doc[self.pos - 1]
def filter(self, value):
"""Only return types that are of intrest like source blocks"""
@ -59,12 +61,11 @@ class Document:
def images(self):
for item in self.__iter__():
if item.token == tokens.IMAGE:
yield item.value[0]
if item.token == tokens.TEXT:
if isinstance(item.value, list):
for token in item.value:
if token.token == tokens.IMAGE:
yield token
yield item
if isinstance(item.value, list):
for token in item.value:
if token.token == tokens.IMAGE:
yield token
def __len__(self):
return len(self.doc)
@ -73,23 +74,26 @@ class Document:
self.index.setdefault(value.token, []).append(len(self.doc))
self.doc.append(value)
def parse_attrs(text):
attrs = {}
value_list = text.split(':')
attrs['language'] = value_list.pop(0).strip()
value_list = text.split(":")
attrs["language"] = value_list.pop(0).strip()
for row in value_list:
values = row.strip().split(' ')
values = row.strip().split(" ")
attrs[values[0]] = values[1:]
return attrs
def parsebody(text, rx):
match = re.search(rx, text)
if match:
return False, None
return rx, text + "\n"
def parseline(text):
attrs=None
attrs = None
for key, (rx, block, s, e, count) in TOKENS.items():
match = re.search(rx, text)
if not match:
@ -97,18 +101,15 @@ def parseline(text):
value = text[match.end() :]
level = len(match.group(0))
if count is True:
attrs={'depth': level}
attrs = {"depth": level}
if key == tokens.META:
return (
block,
Token(token=match.group(0)[s:e], value=value),
)
return (block, Token(token=match.group(0)[s:e], value=value))
if key == tokens.SOURCE:
return block, Token(token=key, attrs=parse_attrs(value))
if key == tokens.TABLE:
return block, Token(token=key, value=text+"\n")
return block, Token(token=key, value=text + "\n")
if key == tokens.BULLET:
return block, Token(token=key, value=text+"\n")
return block, Token(token=key, value=text + "\n")
return block, Token(token=key, value=value, attrs=attrs)
text = text.strip()
@ -122,54 +123,54 @@ def parse_text(txt):
tokenlist = []
def img(char, step):
if char != '[':
if char != "[":
return char
char = next(step, None)
if char != '[':
if char != "[":
return char
char = next(step, None)
path = ''
while char not in [']'] + ESCAPE:
path = ""
while char not in ["]"] + ESCAPE:
path += char
char = next(step, None)
char = next(step, None)
alt = ''
if char == '[':
alt = ""
if char == "[":
char = next(step, None)
while char not in [']'] + ESCAPE:
while char not in ["]"] + ESCAPE:
alt += char
char = next(step, None)
char = next(step, None)
if path.endswith(image_extensions):
tokenlist.append(Token(tokens.IMAGE, [path, alt]))
return ''
return ""
tokenlist.append(Token(tokens.LINK, [path, alt]))
return ''
return ""
def emphasis(char, step, end, tag):
if not char or char!=end:
if not char or char != end:
return char
char = next(step, None)
r = ''
r = ""
while char and char not in [end] + ESCAPE:
r += char
char = next(step, None)
tokenlist.append(Token(tag, r))
return ''
return ""
step = iter(txt)
while char is not None:
char = next(step, None)
char = emphasis(char, step, '*', tokens.BOLD)
char = emphasis(char, step, '/', tokens.ITALIC)
char = emphasis(char, step, '_', tokens.UNDERLINED)
char = emphasis(char, step, '=', tokens.VERBATIM)
char = emphasis(char, step, '~', 'PRE')
char = emphasis(char, step, "*", tokens.BOLD)
char = emphasis(char, step, "/", tokens.ITALIC)
char = emphasis(char, step, "_", tokens.UNDERLINED)
char = emphasis(char, step, "=", tokens.VERBATIM)
char = emphasis(char, step, "~", "PRE")
char = img(char, step)
if not char:
continue
@ -187,7 +188,7 @@ def parse(stream):
doc = Document()
block = False
for line in stream:
line = line.strip('\n')
line = line.strip("\n")
if block is not False:
block, token = parsebody(line, block)
if block:

13
tests/fixtures/test_images.org vendored Normal file
View File

@ -0,0 +1,13 @@
#+TITLE: Emacs org-mode tables
#+AUTHOR: Eric H. Neilsen, Jr.
#+EMAIL: neilsen@fnal.gov
#+DATE: jkkj
#+KEYWORDS: emacs, orgmode, tests
#+DESCRIPTION: Test DESCRIPTION
#+KEYWORDS: key1, key2
Images
[[./images.jpg]]
[[./images.jpg][test]]

17
tests/test_document_functions.py
View File

@ -1,15 +1,30 @@
import os
import pytest
from eorg import tokens
from eorg.tokens import Token
from eorg.parser import parse
def test_fetch_attribute():
with open(os.path.abspath("./tests/fixtures/test.org"), "r") as fp:
doc = parse(fp)
assert doc.title == ' Emacs org-mode examples'
assert doc.title == " Emacs org-mode examples"
def test_fetch_non_existant_attribute():
with open(os.path.abspath("./tests/fixtures/test.org"), "r") as fp:
doc = parse(fp)
with pytest.raises(AttributeError):
doc.fake
def test_fetch_image_list():
with open(os.path.abspath("./tests/fixtures/test_images.org"), "r") as fp:
doc = parse(fp)
expected = [
Token(tokens.IMAGE, ["./images.jpg", ""]),
Token(tokens.IMAGE, ["./images.jpg", "test"]),
]
images = [i for i in doc.images()]
assert len(images) == 2