From e6309590fc6afcd575cb652f0d87a226770e5f6d Mon Sep 17 00:00:00 2001
From: Kovid Goyal <kovid@kovidgoyal.net>
Date: Sat, 20 Jun 2009 09:46:22 -0700
Subject: [PATCH] Improve string_to_authors and use it in more places

---
 src/calibre/devices/jetbook/driver.py   | 3 ++-
 src/calibre/ebooks/lrf/meta.py          | 7 ++-----
 src/calibre/ebooks/metadata/__init__.py | 4 +++-
 src/calibre/ebooks/metadata/imp.py      | 8 ++------
 src/calibre/ebooks/metadata/meta.py     | 7 ++-----
 src/calibre/ebooks/metadata/opf.py      | 8 ++------
 src/calibre/ebooks/metadata/pdf.py      | 8 ++------
 src/calibre/ebooks/metadata/rb.py       | 8 ++------
 src/calibre/ebooks/metadata/rtf.py      | 7 ++-----
 src/calibre/library/database.py         | 7 ++++---
 src/calibre/library/database2.py        | 2 +-
 11 files changed, 24 insertions(+), 45 deletions(-)

diff --git a/src/calibre/devices/jetbook/driver.py b/src/calibre/devices/jetbook/driver.py
index 0d815640b1..2af1b03bf7 100644
--- a/src/calibre/devices/jetbook/driver.py
+++ b/src/calibre/devices/jetbook/driver.py
@@ -9,6 +9,7 @@ from itertools import cycle
 
 from calibre.devices.usbms.driver import USBMS
 from calibre import sanitize_file_name as sanitize
+from calibre.ebooks.metadata import string_to_authors
 
 class JETBOOK(USBMS):
     name           = 'Ectaco JetBook Device Interface'
@@ -118,7 +119,7 @@ class JETBOOK(USBMS):
             match = cls.JETBOOK_FILE_NAME_PATTERN.match(fn)
             if match is not None:
                 mi.title = check_unicode(match.group('title'))
-                authors = match.group('authors').split('&')
+                authors = string_to_authors(match.group('authors'))
                 mi.authors = map(check_unicode, authors)
 
         return mi
diff --git a/src/calibre/ebooks/lrf/meta.py b/src/calibre/ebooks/lrf/meta.py
index 6ec87892d6..af1fad128f 100644
--- a/src/calibre/ebooks/lrf/meta.py
+++ b/src/calibre/ebooks/lrf/meta.py
@@ -19,7 +19,7 @@ import xml.dom.minidom as dom
 from functools import wraps
 
 from calibre.devices.prs500.prstypes import field
-from calibre.ebooks.metadata import MetaInformation
+from calibre.ebooks.metadata import MetaInformation, string_to_authors
 
 BYTE      = "<B"  #: Unsigned char little endian encoded in 1 byte 
 WORD      = "<H"  #: Unsigned short little endian encoded in 2 bytes 
@@ -221,10 +221,7 @@ def get_metadata(stream):
     @param stream: A file like object or an instance of L{LRFMetaFile}
     """
     lrf = stream if isinstance(stream, LRFMetaFile) else LRFMetaFile(stream)
-    au = lrf.author.strip().split(',')
-    authors = []
-    for i in au:
-        authors.extend(i.split('&'))
+    authors = string_to_authors(lrf.author)
     mi = MetaInformation(lrf.title.strip(), authors)
     mi.author = lrf.author.strip()
     mi.comments = lrf.free_text.strip()
diff --git a/src/calibre/ebooks/metadata/__init__.py b/src/calibre/ebooks/metadata/__init__.py
index 81275b4ff6..09632d7bee 100644
--- a/src/calibre/ebooks/metadata/__init__.py
+++ b/src/calibre/ebooks/metadata/__init__.py
@@ -13,8 +13,10 @@ from urlparse import urlparse
 
 from calibre import relpath
 
+_author_pat = re.compile(',?\s+and\s+', re.IGNORECASE)
 def string_to_authors(raw):
-    raw = raw.replace('&&', u'\uffff')
+    raw = _author_pat.sub('&', raw)
+    raw = raw.replace('&&', u'\uffff').replace(',', '&')
     authors = [a.strip().replace(u'\uffff', '&') for a in raw.split('&')]
     return authors
 
diff --git a/src/calibre/ebooks/metadata/imp.py b/src/calibre/ebooks/metadata/imp.py
index 20ab7430b9..e35fc848ef 100644
--- a/src/calibre/ebooks/metadata/imp.py
+++ b/src/calibre/ebooks/metadata/imp.py
@@ -4,7 +4,7 @@ __copyright__ = '2008, Ashish Kulkarni <kulkarni.ashish@gmail.com>'
 
 import sys, os
 
-from calibre.ebooks.metadata import MetaInformation
+from calibre.ebooks.metadata import MetaInformation, string_to_authors
 
 MAGIC = ['\x00\x01BOOKDOUG', '\x00\x02BOOKDOUG']
 
@@ -34,11 +34,7 @@ def get_metadata(stream):
         if title:
             mi.title = title
         if author:
-            src = author.split('&')
-            authors = []
-            for au in src:
-                authors += au.split(',')
-            mi.authors = authors
+            mi.authors = string_to_authors(author)
             mi.author = author
         if category:
             mi.category = category
diff --git a/src/calibre/ebooks/metadata/meta.py b/src/calibre/ebooks/metadata/meta.py
index 9a11ea4fca..a239933710 100644
--- a/src/calibre/ebooks/metadata/meta.py
+++ b/src/calibre/ebooks/metadata/meta.py
@@ -9,7 +9,7 @@ from calibre.utils.config import prefs
 from calibre.ebooks.metadata.opf2 import OPF
 
 from calibre.customize.ui import get_file_type_metadata, set_file_type_metadata
-from calibre.ebooks.metadata import MetaInformation
+from calibre.ebooks.metadata import MetaInformation, string_to_authors
 
 _METADATA_PRIORITIES = [
                        'html', 'htm', 'xhtml', 'xhtm',
@@ -132,10 +132,7 @@ def metadata_from_filename(name, pat=None):
             pass
         try:
             au = match.group('authors')
-            aus = au.split(',')
-            authors = []
-            for a in aus:
-                authors.extend(a.split('&'))
+            aus = string_to_authors(au)
             mi.authors = authors
         except IndexError:
             pass
diff --git a/src/calibre/ebooks/metadata/opf.py b/src/calibre/ebooks/metadata/opf.py
index f508ffd517..701de1e116 100644
--- a/src/calibre/ebooks/metadata/opf.py
+++ b/src/calibre/ebooks/metadata/opf.py
@@ -7,7 +7,7 @@ import uuid
 from urllib import unquote, quote
 
 from calibre.constants import __appname__, __version__
-from calibre.ebooks.metadata import MetaInformation
+from calibre.ebooks.metadata import MetaInformation, string_to_authors
 from calibre.ebooks.BeautifulSoup import BeautifulStoneSoup, BeautifulSoup
 from calibre.ebooks.lrf import entity_to_unicode
 from calibre.ebooks.metadata import Resource, ResourceCollection
@@ -270,11 +270,7 @@ class OPF(MetaInformation):
                 role = 'aut'
             if role == 'aut' and elem.string:
                 raw = self.ENTITY_PATTERN.sub(entity_to_unicode, elem.string)
-                au = raw.split(',')
-                ans = []
-                for i in au:
-                    ans.extend(i.split('&'))
-                return [a.strip() for a in ans]
+                return string_to_authors(raw)
         return []
 
     def get_author_sort(self):
diff --git a/src/calibre/ebooks/metadata/pdf.py b/src/calibre/ebooks/metadata/pdf.py
index 0dcecac740..97961cde7e 100644
--- a/src/calibre/ebooks/metadata/pdf.py
+++ b/src/calibre/ebooks/metadata/pdf.py
@@ -15,7 +15,7 @@ try:
     _imagemagick_loaded = True
 except:
     _imagemagick_loaded = False
-from calibre.ebooks.metadata import MetaInformation, authors_to_string
+from calibre.ebooks.metadata import MetaInformation, string_to_authors, authors_to_string
 from calibre.utils.pdftk import set_metadata as pdftk_set_metadata
 from calibre.utils.podofo import get_metadata as podofo_get_metadata, \
     set_metadata as podofo_set_metadata, Unavailable, get_metadata_quick
@@ -69,12 +69,8 @@ def get_metadata_pypdf(stream):
             if info.title:
                 mi.title = info.title
             if info.author:
-                src = info.author.split('&')
-                authors = []
-                for au in src:
-                    authors += au.split(',')
-                mi.authors = authors
                 mi.author = info.author
+                mi.authors = string_to_authors(info.author)
             if info.subject:
                 mi.category = info.subject
     except Exception, err:
diff --git a/src/calibre/ebooks/metadata/rb.py b/src/calibre/ebooks/metadata/rb.py
index b52e5a4cd8..1f13ce1d9d 100644
--- a/src/calibre/ebooks/metadata/rb.py
+++ b/src/calibre/ebooks/metadata/rb.py
@@ -4,7 +4,7 @@ __copyright__ = '2008, Ashish Kulkarni <kulkarni.ashish@gmail.com>'
 
 import sys, struct
 
-from calibre.ebooks.metadata import MetaInformation
+from calibre.ebooks.metadata import MetaInformation, string_to_authors
 
 MAGIC = '\xb0\x0c\xb0\x0c\x02\x00NUVO\x00\x00\x00\x00'
 
@@ -41,12 +41,8 @@ def get_metadata(stream):
             if key.strip() == 'TITLE':
                 mi.title = value.strip()
             elif key.strip() == 'AUTHOR':
-                src = value.split('&')
-                authors = []
-                for au in src:
-                    authors += au.split(',')
-                mi.authors = authors
                 mi.author = value
+                mi.authors = string_to_authors(value)
     except Exception, err:
         msg = u'Couldn\'t read metadata from rb: %s with error %s'%(mi.title, unicode(err))
         print >>sys.stderr, msg.encode('utf8')
diff --git a/src/calibre/ebooks/metadata/rtf.py b/src/calibre/ebooks/metadata/rtf.py
index bd8b1098c1..b1ee453218 100644
--- a/src/calibre/ebooks/metadata/rtf.py
+++ b/src/calibre/ebooks/metadata/rtf.py
@@ -5,7 +5,7 @@ Edit metadata in RTF files.
 """
 import re, cStringIO, sys
 
-from calibre.ebooks.metadata import MetaInformation
+from calibre.ebooks.metadata import MetaInformation, string_to_authors
 
 title_pat    = re.compile(r'\{\\info.*?\{\\title(.*?)(?<!\\)\}', re.DOTALL)
 author_pat   = re.compile(r'\{\\info.*?\{\\author(.*?)(?<!\\)\}', re.DOTALL)
@@ -76,10 +76,7 @@ def get_metadata(stream):
         category = category_match.group(1).strip()
     mi = MetaInformation(title, author)
     if author:
-        au = author.split(',')
-        mi.authors = []
-        for i in au:
-            mi.authors.extend(i.split('&'))
+        mi.authors = string_to_authors(author)
     mi.comments = comment
     mi.category = category
     return mi
diff --git a/src/calibre/library/database.py b/src/calibre/library/database.py
index 7261aed7ad..72b629db0b 100644
--- a/src/calibre/library/database.py
+++ b/src/calibre/library/database.py
@@ -9,6 +9,7 @@ from zlib import compress, decompress
 
 from calibre.ebooks.metadata import MetaInformation
 from calibre.web.feeds.recipes import migrate_automatic_profile_to_automatic_recipe
+from calibre.ebooks.metadata import string_to_authors
 
 class Concatenate(object):
     '''String concatenation aggregator for sqlite'''
@@ -97,7 +98,7 @@ class LibraryDatabase(object):
             obj = conn.execute('INSERT INTO books(title, timestamp, author_sort) VALUES (?,?,?)',
                                (book['title'], book['timestamp'], authors))
             id = obj.lastrowid
-            authors = authors.split('&')
+            authors = string_to_authors(authors)
             for a in authors:
                 author = conn.execute('SELECT id from authors WHERE name=?', (a,)).fetchone()
                 if author:
@@ -1103,7 +1104,7 @@ ALTER TABLE books ADD COLUMN isbn TEXT DEFAULT "" COLLATE NOCASE;
                 item[col] = val
                 break
         if column == 'authors':
-            val = val.split('&,')
+            val = string_to_authors(val)
             self.set_authors(id, val)
         elif column == 'title':
             self.set_title(id, val)
@@ -1266,7 +1267,7 @@ ALTER TABLE books ADD COLUMN isbn TEXT DEFAULT "" COLLATE NOCASE;
                 mi.authors = ['Unknown']
         authors = []
         for a in mi.authors:
-            authors += a.split('&')
+            authors += string_to_authors(a)
         self.set_authors(id, authors)
         if mi.author_sort:
             self.set_author_sort(id, mi.author_sort)
diff --git a/src/calibre/library/database2.py b/src/calibre/library/database2.py
index e1bbe06ec0..0c5013880f 100644
--- a/src/calibre/library/database2.py
+++ b/src/calibre/library/database2.py
@@ -993,7 +993,7 @@ class LibraryDatabase2(LibraryDatabase):
                 mi.authors = [_('Unknown')]
         authors = []
         for a in mi.authors:
-            authors += a.split('&')
+            authors += string_to_authors(a)
         self.set_authors(id, authors, notify=False)
         if mi.author_sort:
             self.set_author_sort(id, mi.author_sort, notify=False)