GopherProxy

	Rework status content wrapping - toot - Unnamed repository; edit this file 'des…
	Log
	Files
	Refs
	LICENSE
	---
	commit 47b6a830a129bd6a22ca7eda9594966dcc07ce93
	parent f816c6adfe55142ec9e4b568ae539813292dda54
	Author: Ivan Habunek <[email protected]>
	Date: Mon, 24 Apr 2017 16:25:34 +0200

	Rework status content wrapping

	Diffstat:
	toot/app.py \| 54 +++++++++++++++----------------
	toot/utils.py \| 45 +++++++++++++++++++++++++++++++

	2 files changed, 71 insertions(+), 28 deletions(-)
	---
	diff --git a/toot/app.py b/toot/app.py
	@@ -3,12 +3,12 @@ from __future__ import unicode_literals
	from __future__ import print_function

	import curses
	-import re
	import webbrowser

	-from bs4 import BeautifulSoup
	from textwrap import wrap

	+from toot.utils import format_content
	+

	class Color:
	@staticmethod
	@@ -167,14 +167,13 @@ class TimelineApp:
	window.addstr(offset + 2, 2, date, color)
	window.addstr(offset + 3, 2, time, color)

	- window.addstr(offset + 2, 15, status['author']['acct'], color)
	- window.addstr(offset + 3, 15, status['author']['display_name'], color)
	+ window.addstr(offset + 2, 15, status['account']['acct'], color)
	+ window.addstr(offset + 3, 15, status['account']['display_name'], color)

	window.addstr(offset + 4, 1, '─' * (width - 2))

	window.refresh(0, 0, 2, 0, curses.LINES - 4, self.left_width)

	-
	def draw_statuses(self, window):
	for index, status in enumerate(self.statuses):
	offset = 3 * index - 1
	@@ -185,22 +184,30 @@ class TimelineApp:
	window.erase()
	window.box()

	- acct = status['author']['acct']
	- name = status['author']['display_name']
	+ acct = status['account']['acct']
	+ name = status['account']['display_name']

	window.addstr(1, 2, "@" + acct, Color.green())
	window.addstr(2, 2, name, Color.yellow())

	+ y = 4
	text_width = self.right_width - 4

	- y = 4
	for line in status['lines']:
	- for wrapped in wrap(line, text_width):
	- window.addstr(y, 2, wrapped.ljust(text_width))
	- y += 1
	+ wrapped_lines = wrap(line, text_width) if line else ['']
	+ for wrapped_line in wrapped_lines:
	+ window.addstr(y, 2, wrapped_line.ljust(text_width))
	+ y = y + 1
	+
	+ if status['media_attachments']:
	y += 1
	+ for attachment in status['media_attachments']:
	+ url = attachment['text_url'] or attachment['url']
	+ for line in wrap(url, text_width):
	+ window.addstr(y, 2, line)
	+ y += 1

	- window.addstr(y, 2, '─' * text_width)
	+ window.addstr(y, 1, '-' * (text_width + 2))
	y += 1

	window.addstr(y, 2, status['url'])
	@@ -217,20 +224,20 @@ class TimelineApp:


	def parse_status(status):
	- content = status['reblog']['content'] if status['reblog'] else status['con…
	- account = parse_account(status['reblog']['account'] if status['reblog'] el…
	- boosted_by = parse_account(status['account']) if status['reblog'] else None
	-
	- lines = parse_html(content)
	+ _status = status.get('reblog') or status
	+ account = parse_account(_status['account'])
	+ lines = list(format_content(_status['content']))

	created_at = status['created_at'][:19].split('T')
	+ boosted_by = parse_account(status['account']) if status['reblog'] else None

	return {
	- 'author': account,
	+ 'account': account,
	'boosted_by': boosted_by,
	+ 'created_at': created_at,
	'lines': lines,
	+ 'media_attachments': _status['media_attachments'],
	'url': status['url'],
	- 'created_at': created_at,
	}


	@@ -240,12 +247,3 @@ def parse_account(account):
	'acct': account['acct'],
	'display_name': account['display_name'],
	}
	-
	-
	-def parse_html(html):
	- """Attempt to convert html to plain text while keeping line breaks"""
	- return [
	- BeautifulSoup(l, "html.parser").get_text().replace(''', "'")
	- for l in re.split("</?p[^>]*>", html)
	- if l
	- ]
	diff --git a/toot/utils.py b/toot/utils.py
	@@ -0,0 +1,45 @@
	+# -- coding: utf-8 --
	+from __future__ import unicode_literals
	+from __future__ import print_function
	+
	+import re
	+
	+from bs4 import BeautifulSoup
	+
	+
	+def get_text(html):
	+ """Converts html to text, strips all tags."""
	+ return BeautifulSoup(html, "html.parser").get_text().replace(''', "'")
	+
	+
	+def parse_html(html):
	+ """Attempt to convert html to plain text while keeping line breaks.
	+ Returns a list of paragraphs, each being a list of lines.
	+ """
	+ paragraphs = re.split("</?p[^>]*>", html)
	+
	+ # Convert <br>s to line breaks and remove empty paragraphs
	+ paragraphs = [re.split("<br */?>", p) for p in paragraphs if p]
	+
	+ # Convert each line in each paragraph to plain text:
	+ return [[get_text(l) for l in p] for p in paragraphs]
	+
	+
	+def format_content(content):
	+ """Given a Status contents in HTML, converts it into lines of plain text.
	+
	+ Returns a generator yielding lines of content.
	+ """
	+
	+ paragraphs = parse_html(content)
	+
	+ first = True
	+
	+ for paragraph in paragraphs:
	+ if not first:
	+ yield ""
	+
	+ for line in paragraph:
	+ yield line
	+
	+ first = False