emoji -> smiley

dump_html.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python2
 # -*- coding: UTF-8 -*-
 # File: dump_html.py
-# Date: Sun Nov 23 16:37:48 2014 +0800
+# Date: Sat Dec 20 15:58:35 2014 +0800
 # Author: Yuxin Wu <[email protected]>
 
 import sys
@@ -19,7 +19,6 @@ name = ensure_unicode(sys.argv[3])
 output_file = sys.argv[4]
 
 parser = WeChatDBParser(db_file)
-parser.parse()
 msgs = parser.msgs_by_talker[name]
 
 render = HTMLRender(parser, res)

dump_msg.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python2
 # -*- coding: UTF-8 -*-
 # File: dump_msg.py
-# Date: Sat Nov 22 22:32:23 2014 +0800
+# Date: Sat Dec 20 15:58:29 2014 +0800
 # Author: Yuxin Wu <[email protected]>
 
 from lib.parser import WeChatDBParser
@@ -20,7 +20,6 @@ if not os.path.isdir(output_dir):
     sys.exit("Error creating directory {}".format(output_dir))
 
 parser = WeChatDBParser(db_file)
-parser.parse()
 
 for name, msgs in parser.msgs_by_talker.iteritems():
     print u"Writing msgs for {}".format(name)

lib/emoji.py

@@ -1,81 +0,0 @@
-#!/usr/bin/env python2
-# -*- coding: UTF-8 -*-
-# File: emoji.py
-# Date: Sat Dec 20 15:08:45 2014 +0800
-# Author: Yuxin Wu <[email protected]>
-
-import os
-import re
-import json
-LIB_PATH = os.path.dirname(os.path.abspath(__file__))
-
-UNICODE_EMOJI_FILE = os.path.join(LIB_PATH, 'static', 'unicode-emoji.json')
-TENCENT_EMOJI_FILE = os.path.join(LIB_PATH, 'static', 'tencent-emoji.json')
-TENCENT_EXTRAEMOJI_FILE = os.path.join(LIB_PATH,
-                                       'static', 'tencent-emoji-extra.json')
-UNICODE_EMOJI_RE = re.compile(u'[\U00010000-\U0010ffff]|[\u2600-\u2764]|\u2122|\u00a9|\u00ae')
-
-class EmojiProvider(object):
-    def __init__(self, html_replace=True):
-        """ html_replace: replace emojicode by html.
-            otherwise, replace by plain text
-        """
-        self.html_replace = html_replace
-        if not html_replace:
-            raise NotImplementedError()
-
-        # [微笑] -> 0
-        self.tencent_emoji = json.load(open(TENCENT_EMOJI_FILE))
-
-        # some extra emoji from javascript on wx.qq.com
-        extra_emoji = json.load(open(TENCENT_EXTRAEMOJI_FILE))
-        extra_emoji = dict([(u'[' + k + u']', v) for k, v in
-                            extra_emoji.iteritems()])
-        self.tencent_emoji.update(extra_emoji)
-
-        # 1f35c -> "\ue340"
-        #self.unicode_emoji_code = gUnicodeCodeMap
-
-        # u'\U0001f35c' -> "e340"
-        self.unicode_emoji = dict([(unichr(int(k, 16)), hex(ord(v))[2:])
-                                for k, v in
-                                  json.load(open(UNICODE_EMOJI_FILE)).iteritems()])
-        self.used_emoji_id = set()
-
-
-    def gen_replace_elem(self, emoji_id):
-        return '<span class="emoji emoji{}"></span>'.format(emoji_id)
-
-    def _replace_unicode(self, msg):
-        if not UNICODE_EMOJI_RE.findall(msg):
-        # didn't find the code
-            return msg
-        for k, v in self.unicode_emoji.iteritems():
-            if k in msg:
-                self.used_emoji_id.add(v)
-                msg = msg.replace(k, self.gen_replace_elem(v))
-        return msg
-
-    def _replace_tencent(self, msg):
-        if (not '[' in msg or not ']' in msg) \
-           and (not '\:' in msg) and (not '/' in msg):
-            return msg
-        for k, v in self.tencent_emoji.iteritems():
-            if k in msg:
-                self.used_emoji_id.add(v)
-                msg = msg.replace(k, self.gen_replace_elem(v))
-        return msg
-
-    def replace_emojicode(self, msg):
-        """ replace the emoji code in msg
-            return a html
-        """
-        msg = self._replace_unicode(msg)
-        msg = self._replace_tencent(msg)
-        return msg
-
-if __name__ == '__main__':
-    emoji = EmojiProvider()
-    msg = u"[挥手]哈哈呵呵ｈｉｈｉ\U0001f684\u2728\u0001"
-    msg = emoji.replace_emojicode(msg)
-    print msg

lib/parser.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python2
 # -*- coding: UTF-8 -*-
 # File: parser.py
-# Date: Wed Dec 17 23:04:54 2014 +0800
+# Date: Sat Dec 20 15:58:16 2014 +0800
 # Author: Yuxin Wu <[email protected]>
 
 import sqlite3
@@ -30,6 +30,7 @@ class WeChatDBParser(object):
         self.cc = self.db_conn.cursor()
         self.contacts = {}
         self.msgs_by_talker = defaultdict(list)
+        self.parse()
 
     def _parse_contact(self):
         contacts = self.cc.execute(

lib/render.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python2
 # -*- coding: UTF-8 -*-
 # File: render.py
-# Date: Sat Dec 20 15:40:19 2014 +0800
+# Date: Sat Dec 20 17:48:48 2014 +0800
 # Author: Yuxin Wu <[email protected]>
 
 import os
@@ -20,7 +20,7 @@ except:
 
 from .msg import *
 from .utils import ensure_unicode
-from emoji import EmojiProvider
+from smiley import SmileyProvider
 
 TEMPLATES_FILES = {TYPE_MSG: "TP_MSG",
                    TYPE_IMG: "TP_IMG",
@@ -36,12 +36,12 @@ class HTMLRender(object):
         self.res = res
         if self.res is None:
             logger.warn("Resource Directory not given. Images / Voice Message won't be displayed.")
-        self.emoji = EmojiProvider()
+        self.smiley = SmileyProvider()
 
         csss = glob.glob(os.path.join(LIB_PATH, 'static/*.css'))
         css_string = []
         for css in csss:
-            logger.info("Loading {}.".format(os.path.basename(css)))
+            logger.info("Loading {}".format(os.path.basename(css)))
             css = ensure_unicode(css_compress(open(css).read()))
             css = u'<style type="text/css">{}</style>'.format(css)
             css_string.append(css)
@@ -71,7 +71,7 @@ class HTMLRender(object):
         def fallback():
             template = ensure_unicode(TEMPLATES[1])
             content = msg.msg_str()
-            content = self.emoji.replace_emojicode(content)
+            content = self.smiley.replace_smileycode(content)
             return template.format(sender_label=sender,
                                    content=content)
         if msg.type not in TEMPLATES:
@@ -94,6 +94,12 @@ class HTMLRender(object):
             return template.format(sender_label=sender,
                                    small_img=smallimg,
                                    big_img=bigimg)
+        elif msg.type == TYPE_EMOJI:
+            imgpath = msg.imgPath
+            print imgpath
+            return fallback()
+            # custom emoji
+
         return fallback()
 
     def render_msgs(self, msgs):

lib/res.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python2
 # -*- coding: UTF-8 -*-
 # File: res.py
-# Date: Sat Dec 20 15:40:33 2014 +0800
+# Date: Sat Dec 20 16:26:51 2014 +0800
 # Author: Yuxin Wu <[email protected]>
 
 import glob
@@ -16,6 +16,7 @@ logger = logging.getLogger(__name__)
 from lib.avatar import AvatarReader
 
 VOICE_DIRNAME = 'voice2'
+IMG_DIRNAME = 'image2'
 JPEG_QUALITY = 50
 
 class Resource(object):
@@ -23,7 +24,7 @@ class Resource(object):
     def __init__(self, res_dir):
         assert os.path.isdir(res_dir), "No such directory: {}".format(res_dir)
         self.res_dir = res_dir
-        self.img_dir = os.path.join(res_dir, 'image2')
+        self.img_dir = os.path.join(res_dir, IMG_DIRNAME)
         assert os.path.isdir(self.img_dir), \
                      "No such directory: {}".format(self.img_dir)
         self.avt_reader = AvatarReader(self.res_dir)

lib/smiley.py

@@ -0,0 +1,81 @@
+#!/usr/bin/env python2
+# -*- coding: UTF-8 -*-
+# File: smiley.py
+# Date: Sat Dec 20 17:49:42 2014 +0800
+# Author: Yuxin Wu <[email protected]>
+
+import os
+import re
+import json
+LIB_PATH = os.path.dirname(os.path.abspath(__file__))
+
+UNICODE_SMILEY_FILE = os.path.join(LIB_PATH, 'static', 'unicode-smiley.json')
+TENCENT_SMILEY_FILE = os.path.join(LIB_PATH, 'static', 'tencent-smiley.json')
+TENCENT_EXTRASMILEY_FILE = os.path.join(LIB_PATH,
+                                       'static', 'tencent-smiley-extra.json')
+UNICODE_SMILEY_RE = re.compile(u'[\U00010000-\U0010ffff]|[\u2600-\u2764]|\u2122|\u00a9|\u00ae')
+
+class SmileyProvider(object):
+    def __init__(self, html_replace=True):
+        """ html_replace: replace smileycode by html.
+            otherwise, replace by plain text
+        """
+        self.html_replace = html_replace
+        if not html_replace:
+            raise NotImplementedError()
+
+        # [微笑] -> 0
+        self.tencent_smiley = json.load(open(TENCENT_SMILEY_FILE))
+
+        # some extra smiley from javascript on wx.qq.com
+        extra_smiley = json.load(open(TENCENT_EXTRASMILEY_FILE))
+        extra_smiley = dict([(u'[' + k + u']', v) for k, v in
+                            extra_smiley.iteritems()])
+        self.tencent_smiley.update(extra_smiley)
+
+        # 1f35c -> "\ue340"
+        #self.unicode_smiley_code = gUnicodeCodeMap
+
+        # u'\U0001f35c' -> "e340"
+        self.unicode_smiley = dict([(unichr(int(k, 16)), hex(ord(v))[2:])
+                                for k, v in
+                                  json.load(open(UNICODE_SMILEY_FILE)).iteritems()])
+        self.used_smiley_id = set()
+
+
+    def gen_replace_elem(self, smiley_id):
+        return '<span class="smiley smiley{}"></span>'.format(smiley_id)
+
+    def _replace_unicode(self, msg):
+        if not UNICODE_SMILEY_RE.findall(msg):
+        # didn't find the code
+            return msg
+        for k, v in self.unicode_smiley.iteritems():
+            if k in msg:
+                self.used_smiley_id.add(v)
+                msg = msg.replace(k, self.gen_replace_elem(v))
+        return msg
+
+    def _replace_tencent(self, msg):
+        if (not '[' in msg or not ']' in msg) \
+           and (not '\:' in msg) and (not '/' in msg):
+            return msg
+        for k, v in self.tencent_smiley.iteritems():
+            if k in msg:
+                self.used_smiley_id.add(v)
+                msg = msg.replace(k, self.gen_replace_elem(v))
+        return msg
+
+    def replace_smileycode(self, msg):
+        """ replace the smiley code in msg
+            return a html
+        """
+        msg = self._replace_unicode(msg)
+        msg = self._replace_tencent(msg)
+        return msg
+
+if __name__ == '__main__':
+    smiley = SmileyProvider()
+    msg = u"[挥手]哈哈呵呵ｈｉｈｉ\U0001f684\u2728\u0001"
+    msg = smiley.replace_smileycode(msg)
+    print msg

lib/static/gen_smiley_css.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python2
 # -*- coding: UTF-8 -*-
 # File: gen_emoji_css.py
-# Date: Mon Dec 15 22:15:54 2014 +0800
+# Date: Sat Dec 20 17:50:57 2014 +0800
 # Author: Yuxin Wu <[email protected]>
 
 import os
@@ -9,9 +9,9 @@ import glob
 import base64
 
 DIR_PATH = os.path.dirname(os.path.abspath(__file__))
-OUTPUT_FILE = os.path.join(DIR_PATH, 'emoji.css')
+OUTPUT_FILE = os.path.join(DIR_PATH, 'smiley.css')
 
-HEAD = """.emoji {
+HEAD = """.smiley {
     background-position: -2px -2px;
     background-repeat: norepeat;
     width: 20px;
@@ -22,7 +22,7 @@ HEAD = """.emoji {
 }
 """
 
-TEMPLATE = """.emoji{name} {{
+TEMPLATE = """.smiley{name} {{
     background-image: url("data:image/png;base64,{b64}");
 }}"""
 
@@ -32,8 +32,8 @@ def get_file_b64(fname):
 
 with open(OUTPUT_FILE, 'w') as f:
     print >> f, HEAD
-    for fname in glob.glob(os.path.join(DIR_PATH, 'emojis', '*.png')):
+    for fname in glob.glob(os.path.join(DIR_PATH, 'smileys', '*.png')):
         b64 = get_file_b64(fname)
         basename = os.path.basename(fname)
-        emojiname = basename[:-4]
-        print >> f, TEMPLATE.format(name=emojiname, b64=b64);
+        smileyname = basename[:-4]
+        print >> f, TEMPLATE.format(name=smileyname, b64=b64);

lib/static/parse_tencent_smiley.py

@@ -1,20 +1,18 @@
 #!/usr/bin/env python2
 # -*- coding: UTF-8 -*-
 # File: parse_tencent_emoji.py
-# Date: Tue Dec 16 23:22:50 2014 +0800
+# Date: Sat Dec 20 17:52:20 2014 +0800
 # Author: Yuxin Wu <[email protected]>
 
 import xml.etree.ElementTree as ET
 import os
 import json
 
-NUM_EMOJI = 105
-
 tree = ET.parse(os.path.join(
-    os.path.dirname(os.path.abspath(__file__)), 'emoji.xml'))
+    os.path.dirname(os.path.abspath(__file__)), 'smiley.xml'))
 root = tree.getroot()
 
-emojis = {}
+smileys = {}
 for child in root:
     name = child.attrib['name']
     if 'smiley_values' in name:
@@ -25,8 +23,8 @@ for child in root:
         for idx, v in enumerate(lst):
             if type(v) == str:
                 v = v.decode('utf-8')
-            emojis[v] = idx
+            smileys[v] = idx
 
-with open('tencent-emoji.json', 'w') as f:
-    json.dump(emojis, f)
+with open('tencent-smiley.json', 'w') as f:
+    json.dump(smileys, f)