tris/recoll
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

updated to work with 1.19

Browse Source
This commit is contained in:
Jean-Francois Dockes 2014-03-22 16:20:59 +01:00
parent 52921c3900
commit 09499112d7
1 changed files with 12 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
src/python/samples/rclmbox.py
View File

@ -6,13 +6,16 @@ import mailbox
import email.header import email.header
import email.utils import email.utils
#import sys #import sys
import recoll try:
from recoll import recoll
except:
import recoll
import os import os
import stat import stat
#mbfile = "/Users/dockes/projets/fulltext/testrecoll/mail/fred" mbfile = os.path.expanduser("~/mbox")
mbfile = "/Users/dockes/mail/outmail" rclconf = os.path.expanduser("~/.recoll")
rclconf = "/Users/dockes/.recoll-test"
def header_value(msg, nm, to_utf = False): def header_value(msg, nm, to_utf = False):
value = msg.get(nm) value = msg.get(nm)
@ -49,9 +52,11 @@ class mbox_indexer:
def index(self, db): def index(self, db):
if not db.needUpdate(self.udi(1), self.sig()): if not db.needUpdate(self.udi(1), self.sig()):
print("Index is up to date");
return None return None
mb = mailbox.mbox(self.mbfile) mb = mailbox.mbox(self.mbfile)
for msg in mb.values(): for msg in mb.values():
print("Indexing message %d" % self.msgnum);
self.index_message(db, msg) self.index_message(db, msg)
self.msgnum += 1 self.msgnum += 1
@ -90,14 +95,13 @@ class mbox_indexer:
text += u"\n" text += u"\n"
for part in msg.walk(): for part in msg.walk():
if part.is_multipart(): if part.is_multipart():
pass #print "Multipart: " + part.get_content_type() pass
else: else:
ct = part.get_content_type() ct = part.get_content_type()
#print "Simple: " + ct
if ct.lower() == "text/plain": if ct.lower() == "text/plain":
charset = part.get_content_charset("iso-8859-1") charset = part.get_content_charset("iso-8859-1")
print "charset: ", charset #print "charset: ", charset
print "text: ", part.get_payload(None, True) #print "text: ", part.get_payload(None, True)
text += unicode(part.get_payload(None, True), charset) text += unicode(part.get_payload(None, True), charset)
doc.text = text doc.text = text
# dbytes # dbytes