Merge branch 'bugfixes-0.1.2' into prepare-release

Conflicts:
	docs/conf.py
	setup.py

Author: Pietro Albini

botogram/syntaxes.py

@@ -8,6 +8,8 @@
 
 import re
 
+from . import utils
+
 
 _markdown_re = re.compile(r".*("
                           r"\*(.*)\*|"
@@ -30,11 +32,16 @@
 
 def is_markdown(message):
     """Check if a string is actually markdown"""
+    # Don't mark part of URLs or email addresses as Markdown
+    message = utils.strip_urls(message)
+
     return bool(_markdown_re.match(message))
 
 
 def is_html(message):
     """Check if a string is actually HTML"""
+    # Here URLs are not stripped because no sane URL contains HTML tags in it,
+    # and for a few cases the speed penality is not worth
     return bool(_html_re.match(message))
 
 
@@ -48,7 +55,9 @@ def guess_syntax(message, provided):
         else:
             return None
 
-    if provided in ("md", "markdown", "Markdown"):
+    if provided in ("plain",):
+        return None
+    elif provided in ("md", "markdown", "Markdown"):
         return "Markdown"
     elif provided in ("html", "HTML"):
         return "HTML"

botogram/utils.py

@@ -17,9 +17,12 @@
 import logbook
 import functools
 
+# URLs regex created by http://twitter.com/imme_emosol
+
 _username_re = re.compile(r"\@([a-zA-Z0-9_]{5}[a-zA-Z0-9_]*)")
 _command_re = re.compile(r"^\/[a-zA-Z0-9_]+(\@[a-zA-Z0-9_]{5}[a-zA-Z0-9_]*)?$")
 _email_re = re.compile(r"[a-zA-Z0-9_\.\+\-]+\@[a-zA-Z0-9_\.\-]+\.[a-zA-Z]+")
+_url_re = re.compile(r"https?://(-\.)?([^\s/?\.#-]+\.?)+(/[^\s]*)?")
 
 # This small piece of global state will track if logbook was configured
 _logger_configured = False
@@ -139,15 +142,22 @@ def docstring_of(func, bot=None, component_id=None):
     return format_docstr(docstring)
 
 
+def strip_urls(string):
+    """Strip URLs and emails from a string"""
+    string = _url_re.sub("", string)
+    string = _email_re.sub("", string)
+    return string
+
+
 def usernames_in(message):
     """Return all the matched usernames in the message"""
     # Don't parse usernames in the commands
     if _command_re.match(message.split(" ", 1)[0]):
         message = message.split(" ", 1)[1]
 
     # Strip email addresses from the message, in order to avoid matching the
-    # user's domain. This also happens to match username/passwords in URLs
-    message = _email_re.sub("", message)
+    # user's domain. Also strip URLs, in order to avoid usernames in them.
+    message = strip_urls(message)
 
     results = []
     for result in _username_re.finditer(message):

docs/buildthedocs.yml

@@ -13,7 +13,7 @@ versions:
     source:
       provider: git
       url: .
-      checkout: release-0.1
+      checkout: v0.1.1
     directory: docs
     title: botogram 0.1
     notice: alpha

docs/changelog.rst

@@ -9,6 +9,28 @@ botogram changelog
 
 Here you can see what changed in every botogram release.
 
+.. _changelog-0.2:
+
+botogram 0.2
+=============
+
+*Alpha release, not yet released*
+
+No changes yet.
+
+.. _changelog-0.1.2:
+
+botogram 0.1.2
+==============
+
+*Bugfix release, not yet released*
+
+* Add a way to disable the syntax detector (`issue 27`_)
+* Fix automatic syntax detector recognizing markdown in URLs (`issue 28`_)
+
+.. _issue 27: https://github.com/pietroalbini/botogram/issues/27
+.. _issue 28: https://github.com/pietroalbini/botogram/issues/28
+
 .. _changelog-0.1.1:
 
 botogram 0.1.1

docs/tricks.rst

@@ -71,6 +71,13 @@ That parameter accepts the following values:
 * ``markdown``, or its aliases ``md`` and ``Markdown``
 * ``html``, or its alias ``HTML``
 
+Also, if you don't want to use any rich formatting but the detector spots
+something, you can disable it providing the special syntax ``plain`` to it:
+
+.. code-block:: python
+
+   chat.send("*I don't want this to be detected*", syntax="plain")
+
 .. note::
 
    Support for rich formatting depends on your users' Telegram client. If

setup.py

@@ -26,7 +26,7 @@ def hello_command(chat, message, args):
     if __name__ == "__main__":
         bot.run()
 
-Want to get started? `Go to the documentation_`
+Want to get started? `Go to the documentation`_
 
 .. _Telegram bots: https://core.telegram.org/bots
 .. _Go to the documentation: https://botogram.pietroalbini.io/docs

tests/test_syntaxes.py

@@ -21,6 +21,9 @@ def test_is_markdown():
     assert botogram.syntaxes.is_markdown("[a](b)")
     assert botogram.syntaxes.is_markdown("![a](b)!")
 
+    assert not botogram.syntaxes.is_markdown("hey@this_is_awesome.com")
+    assert not botogram.syntaxes.is_markdown("https://www.this_is_awesome.com")
+
 
 def test_is_html():
     assert not botogram.syntaxes.is_html("not HTML, sorry!")
@@ -38,6 +41,9 @@ def test_is_html():
 
 def test_guess_syntax():
     # Provided syntax name
+    for name in ("plain",):
+        assert botogram.syntaxes.guess_syntax("", name) is None
+
     for name in ("md", "markdown", "Markdown"):
         assert botogram.syntaxes.guess_syntax("", name) == "Markdown"