From 8335706321158cf47aec2d11f562186914f71b09 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal@gmail.com>
Date: Sun, 2 Nov 2014 13:19:05 +1100
Subject: [PATCH] * Add LIKE_URL and LIKE_NUMBER flag features

---
 spacy/lexeme.pxd | 3 +++
 spacy/lexeme.pyx | 3 +++
 spacy/orth.py    | 6 +++---
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/spacy/lexeme.pxd b/spacy/lexeme.pxd
index 76b236e5b..288fd6375 100644
--- a/spacy/lexeme.pxd
+++ b/spacy/lexeme.pxd
@@ -16,6 +16,9 @@ cpdef enum:
     IS_TITLE
     IS_UPPER
 
+    LIKE_URL
+    LIKE_NUMBER
+
     OFT_LOWER
     OFT_TITLE
     OFT_UPPER
diff --git a/spacy/lexeme.pyx b/spacy/lexeme.pyx
index 6616cda47..c7c9e8334 100644
--- a/spacy/lexeme.pyx
+++ b/spacy/lexeme.pyx
@@ -23,6 +23,9 @@ def get_flags(unicode string, float upper_pc, float title_pc, float lower_pc):
     flags |= orth.is_space(string) << IS_SPACE
     flags |= orth.is_title(string) << IS_TITLE
     flags |= orth.is_upper(string) << IS_UPPER
+
+    flags |= orth.like_url(string) << LIKE_URL
+    flags |= orth.like_number(string) << LIKE_NUMBER
     return flags
 
 
diff --git a/spacy/orth.py b/spacy/orth.py
index 10a5df66c..e27ef9119 100644
--- a/spacy/orth.py
+++ b/spacy/orth.py
@@ -65,7 +65,7 @@ TLDs = set("com|org|edu|gov|net|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|mu
         "wf|ws|ye|yt|za|zm|zw".split('|'))
 
 
-def is_urlish(string):
+def like_url(string):
     # We're looking for things that function in text like URLs. So, valid URL
     # or not, anything they say http:// is going to be good.
     if string.startswith('http://'):
@@ -89,14 +89,14 @@ NUM_WORDS = set('zero one two three four five six seven eight nine ten'
                 'eighteen nineteen twenty thirty forty fifty sixty seventy'
                 'eighty ninety hundred thousand million billion trillion'
                 'quadrillion gajillion bazillion'.split())
-def is_number(string):
+def like_number(string):
     string = string.replace(',', '')
     string = string.replace('.', '')
     if string.isdigit():
         return True
     if string.count('/') == 1:
         num, denom = string.split('/')
-        if is_number(num) and is_number(denom):
+        if like_number(num) and like_number(denom):
             return True
     if string in NUM_WORDS:
         return True