commit 347448c5827b68f1ff40c0cfdd34c7b62f863a0a
parent 867822dfb3f57e83c93f5e48bacd5a591829f148
Author: Martin Schanzenbach <mschanzenbach@posteo.de>
Date: Thu, 2 Sep 2021 22:54:40 +0200
port to python3; add buildbot scripts
Diffstat:
8 files changed, 79 insertions(+), 68 deletions(-)
diff --git a/.buildbot/build.sh b/.buildbot/build.sh
@@ -0,0 +1,3 @@
+#!/bin/bash
+
+make
diff --git a/.buildbot/firefly-x86_64-amdepyc_deploy.sh b/.buildbot/firefly-x86_64-amdepyc_deploy.sh
@@ -0,0 +1,7 @@
+#!/bin/bash
+
+# Deploy bib from buildbot
+
+chmod -R ag+rX .
+DEPLOY_USER="www"
+rsync -a --delete . $DEPLOY_USER@firefly.gnunet.org:~/bib/
diff --git a/BibTeX.py b/BibTeX.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python2
+#!/usr/bin/python3
# Copyright 2003-2008, Nick Mathewson. See LICENSE for licensing info.
# Copyright 2018, 2019 ng0 <ng0@n0.is>.
@@ -7,9 +7,9 @@ BibTeX.py -- parse and manipulate BibTeX files and entries.
Based on perl code by Eddie Kohler; heavily modified.
"""
-from __future__ import print_function
+
from future.utils import raise_with_traceback
-import cStringIO
+from io import StringIO ## for Python 3
import re
import sys
import os
@@ -104,8 +104,8 @@ class BibTeX:
if cr.entryLine < ent.entryLine:
print("Warning: crossref %s used after declaration"%cr.key)
- for k in cr.entries.keys():
- if ent.entries.has_key(k):
+ for k in list(cr.entries.keys()):
+ if k in ent.entries:
print("ERROR: %s defined both in %s and in %s"
%(k, ent.key, cr.key))
else:
@@ -118,9 +118,9 @@ class BibTeX:
# hack: if no key is required, require "title", since every
# entry will have a title.
rk = "title"
-
+ print("rk is " + rk)
for ent in self.entries:
- if ent.type in config.OMIT_ENTRIES or not ent.has_key(rk):
+ if ent.type in config.OMIT_ENTRIES or rk not in ent.entries.keys():
ent.check()
del self.byKey[ent.key.lower()]
else:
@@ -138,7 +138,7 @@ def buildAuthorTable(entries):
authorsByLast.setdefault(tuple(a.last), []).append(a)
# map from author to collapsed author.
result = {}
- for k, v in config.COLLAPSE_AUTHORS.items():
+ for k, v in list(config.COLLAPSE_AUTHORS.items()):
a = parseAuthor(k)[0]
c = parseAuthor(v)[0]
result[c] = c
@@ -146,7 +146,7 @@ def buildAuthorTable(entries):
for e in entries:
for author in e.parsedAuthor:
- if result.has_key(author):
+ if author in result:
continue
c = author
@@ -157,7 +157,7 @@ def buildAuthorTable(entries):
result[author] = c
if 0:
- for a, c in result.items():
+ for a, c in list(result.items()):
if a != c:
print("Collapsing authors: %s => %s" % (a, c))
if 0:
@@ -253,7 +253,7 @@ def splitEntriesByAuthor(entries):
htmlResult[sortkey] = secname
result.setdefault(sortkey, []).append(ent)
- sortnames = result.keys()
+ sortnames = list(result.keys())
sortnames.sort()
sections = [(htmlResult[n], result[n]) for n in sortnames]
return sections, url_map
@@ -326,7 +326,7 @@ class BibTeXEntry:
return self.entries.get(k, v)
def has_key(self, k):
- return self.entries.has_key(k)
+ return k in self.entries
def __getitem__(self, k):
return self.entries[k]
@@ -358,25 +358,25 @@ class BibTeXEntry:
d = ["@%s{%s,\n" % (self.type, self.key)]
if v:
df = DISPLAYED_FIELDS[:]
- for k in self.entries.keys():
+ for k in list(self.entries.keys()):
if k not in df:
df.append(k)
else:
df = DISPLAYED_FIELDS
for f in df:
- if not self.entries.has_key(f):
+ if f not in self.entries:
continue
v = self.entries[f]
if v.startswith("<span class='bad'>"):
d.append("%%%%% ERROR: Missing field\n")
d.append("%% %s = {?????},\n"%f)
continue
- np = v.translate(ALLCHARS, PRINTINGCHARS)
+ np = v.translate(str.maketrans(ALLCHARS, ALLCHARS, PRINTINGCHARS))
if np:
d.append("%%%%% "+("ERROR: Non-ASCII characters: '%r'\n"%np))
d.append(" ")
v = v.replace("&", "&")
- if invStrings.has_key(v):
+ if v in invStrings:
s = "%s = %s,\n" %(f, invStrings[v])
else:
s = "%s = {%s},\n" % (f, v)
@@ -469,7 +469,7 @@ class BibTeXEntry:
"(%r) doesn't start with 'Proceedings of'"
% (self.entryLine, selfself.key, self['booktitle']))
- if self.has_key("pages") and not re.search(r'\d+--\d+', self['pages']):
+ if "pages" in self.entries.keys() and not re.search(r'\d+--\d+', self.entries['pages']):
errs.append("ERROR (record %s):\t Misformed pages in %s"
% (self.entryLine, self.key))
@@ -479,8 +479,8 @@ class BibTeXEntry:
"it should have a booktitle, not a title."
% (self.entryLine, self.key))
- for field, value in self.entries.items():
- if value.translate(ALLCHARS, PRINTINGCHARS):
+ for field, value in list(self.entries.items()):
+ if value.translate(str.maketrans(ALLCHARS, ALLCHARS, PRINTINGCHARS)):
errs.append("ERROR (record %s):\t %s.%s "
"has non-ASCII characters"
% (self.entryLine, self.key, field))
@@ -806,7 +806,7 @@ def htmlize(s):
s = unTeXescapeURL(s)
s = RE_LIGATURE.sub(_unlig_html, s)
s = RE_TEX_CMD.sub("", s)
- s = s.translate(ALLCHARS, "{}")
+ s = s.translate(str.maketrans(ALLCHARS, ALLCHARS, "{}"))
s = RE_PAGE_SPAN.sub(lambda m: "%s-%s"%(m.groups()), s)
s = s.replace("---", "—")
s = s.replace("--", "–")
@@ -829,7 +829,7 @@ def txtize(s):
s = RE_ACCENT.sub(lambda m: "%s" % m.group(2), s)
s = RE_LIGATURE.sub(lambda m: "%s%s"%m.groups(), s)
s = RE_TEX_CMD.sub("", s)
- s = s.translate(ALLCHARS, "{}")
+ s = s.translate(str.maketrans(ALLCHARS, ALLCHARS, "{}"))
return s
PROCEEDINGS_RE = re.compile(r'((?:proceedings|workshop record) of(?: the)? )(.*)', re.I)
@@ -983,7 +983,7 @@ def _split(s, w=79, indent=8):
first = 1
indentation = ""
while len(s) > w:
- for i in xrange(w-1, 20, -1):
+ for i in range(w-1, 20, -1):
if s[i] == ' ':
r.append(indentation+s[:i])
s = s[i+1:]
@@ -1005,14 +1005,14 @@ class FileIter:
if fname:
file = open(fname, 'r')
if string:
- file = cStringIO.StringIO(string)
+ file = StringIO(string)
if file:
- it = iter(file.xreadlines())
+ it = iter(file)
self.iter = it
assert self.iter
self.lineno = 0
- self._next = it.next
- def next(self):
+ self._next = it.__next__
+ def __next__(self):
self.lineno += 1
return self._next()
@@ -1034,7 +1034,7 @@ def _parseAuthor(s):
while s:
s = s.strip()
bracelevel = 0
- for i in xrange(len(s)):
+ for i in range(len(s)):
if s[i] == '{':
bracelevel += 1
elif s[i] == '}':
@@ -1090,9 +1090,9 @@ def _parseAuthor(s):
return parsedAuthors
-ALLCHARS = "".join(map(chr, range(256)))
+ALLCHARS = "".join(map(chr, list(range(256))))
-PRINTINGCHARS = "\t\n\r"+"".join(map(chr, range(32, 127)))
+PRINTINGCHARS = "\t\n\r"+"".join(map(chr, list(range(32, 127))))
LC_CHARS = "abcdefghijklmnopqrstuvwxyz"
@@ -1108,10 +1108,10 @@ def split_von(f, v, l, x):
tt = t = x[0]
del x[0]
if tt[:2] == '{\\':
- tt = tt.translate(ALLCHARS, SV_DELCHARS)
+ tt = tt.translate(str.maketrans(ALLCHARS, ALLCHARS, SV_DELCHARS))
tt = RE_ESCAPED.sub("", tt)
- tt = tt.translate(ALLCHARS, "{}")
- if tt.translate(ALLCHARS, LC_CHARS) == "":
+ tt = tt.translate(str.maketrans(ALLCHARS, ALLCHARS, "{}"))
+ if tt.translate(str.maketrans(ALLCHARS, ALLCHARS, LC_CHARS)) == "":
v.append(t)
in_von = 1
elif in_von and f is not None:
@@ -1145,7 +1145,7 @@ class Parser:
self.strings.update(initial_strings)
self.newStrings = {}
self.invStrings = {}
- for k, v in config.INITIAL_STRINGS.items():
+ for k, v in list(config.INITIAL_STRINGS.items()):
self.invStrings[v] = k
self.fileiter = fileiter
if result is None:
@@ -1200,7 +1200,7 @@ class Parser:
continue
data.append(line)
data.append(" ")
- line = it.next()
+ line = next(it)
self.litStringLine = 0
elif line[0] == '{':
bracelevel += 1
@@ -1227,7 +1227,7 @@ class Parser:
#print bracelevel, "C", repr(line)
data.append(line)
data.append(" ")
- line = it.next()
+ line = next(it)
elif line[0] == '#':
print("Weird concat on line %s"%it.lineno,
file=sys.stderr)
@@ -1321,7 +1321,7 @@ class Parser:
else:
key = v[0]
d = {}
- for i in xrange(1, len(v), 2):
+ for i in range(1, len(v), 2):
d[v[i].lower()] = v[i+1]
ent = BibTeXEntry(self.curEntType, key, d)
ent.entryLine = self.entryLine
@@ -1348,13 +1348,13 @@ class Parser:
def _parse(self):
it = self.fileiter
- line = it.next()
+ line = next(it)
while 1:
# Skip blank lines.
while not line \
or line.isspace() \
or OUTER_COMMENT_RE.match(line):
- line = it.next()
+ line = next(it)
# Get the first line of an entry.
m = ENTRY_BEGIN_RE.match(line)
if m:
@@ -1371,7 +1371,7 @@ def _advance(it, line):
while not line \
or line.isspace() \
or COMMENT_RE.match(line):
- line = it.next()
+ line = next(it)
return line
# Matches a comment line outside of an entry.
diff --git a/Makefile b/Makefile
@@ -1,4 +1,4 @@
-PYTHON=python2
+PYTHON=python3
VERSION=0.3-dev
all:
diff --git a/anonbib.cfg b/anonbib.cfg
@@ -234,4 +234,4 @@ TAG_DIRECTORIES = {'': "full", "selected": ""}
MULTI_VAL_FIELDS = ["www_section"]
# Make cached stuff group-writable. Make sure that your cache directories
# are sticky!
-CACHE_UMASK = 002
+CACHE_UMASK = 0o002
diff --git a/config.py b/config.py
@@ -22,7 +22,7 @@ def load(cfgFile):
Load config FILE
"""
mod = {}
- execfile(cfgFile, mod)
+ exec(compile(open(cfgFile, "rb").read(), cfgFile, 'exec'), mod)
for _k in _KEYS:
try:
globals()[_k] = mod[_k]
@@ -31,7 +31,7 @@ def load(cfgFile):
INITIAL_STRINGS.update(_EXTRA_INITIAL_STRINGS)
AUTHOR_RE_LIST[:] = [
- (re.compile(k, re.I), v,) for k, v in AUTHOR_URLS.items()
+ (re.compile(k, re.I), v,) for k, v in list(AUTHOR_URLS.items())
]
NO_COLLAPSE_AUTHORS_RE_LIST[:] = [
@@ -39,7 +39,7 @@ def load(cfgFile):
]
ALPHABETIZE_AUTHOR_AS_RE_LIST[:] = [
- (re.compile(k, re.I), v,) for k, v in ALPHABETIZE_AUTHOR_AS.items()
+ (re.compile(k, re.I), v,) for k, v in list(ALPHABETIZE_AUTHOR_AS.items())
]
_EXTRA_INITIAL_STRINGS = {
diff --git a/rank.py b/rank.py
@@ -32,15 +32,15 @@ def cache_folder():
return r
import re
-from urllib2 import urlopen, build_opener
-from urllib import quote
+from urllib.request import urlopen, build_opener
+from urllib.parse import quote
from datetime import date
import hashlib
# A more handy hash
def md5h(s):
m = hashlib.md5()
- m.update(s)
+ m.update(s.encode('utf-8'))
return m.hexdigest()
format_tested = 0
@@ -66,17 +66,17 @@ def getPageForTitle(title, cache=True, update=True, save=True):
if exists(join(cache_folder(), md5h(url))) and cache:
return url, file(join(cache_folder(), md5h(url)),'r').read()
elif update:
- print "Downloading rank for %r."%title
+ print(("Downloading rank for %r."%title))
# Make a custom user agent (so that we are not filtered by Google)!
opener = build_opener()
opener.addheaders = [('User-agent', 'Anon.Bib.0.1')]
- print "connecting..."
+ print("connecting...")
connection = opener.open(url)
- print "reading"
+ print("reading")
page = connection.read()
- print "done"
+ print("done")
if save:
file(join(cache_folder(), md5h(url)),'w').write(page)
return url, page
@@ -140,20 +140,20 @@ def get_rank_html(title, years=None, base_url=".", update=True,
def TestScholarFormat():
# We need to ensure that Google Scholar does not change its page format under our feet
# Use some cases to check if all is good
- print "Checking google scholar formats..."
+ print("Checking google scholar formats...")
stopAndGoCites = getCite("Stop-and-Go MIXes: Providing Probabilistic Anonymity in an Open System", False)[0]
dragonCites = getCite("Mixes protected by Dragons and Pixies: an empirical study", False, save=False)[0]
if stopAndGoCites in (0, None):
- print """OOPS.\n
+ print("""OOPS.\n
It looks like Google Scholar changed their URL format or their output format.
-I went to count the cites for the Stop-and-Go MIXes paper, and got nothing."""
+I went to count the cites for the Stop-and-Go MIXes paper, and got nothing.""")
sys.exit(1)
if dragonCites != None:
- print """OOPS.\n
+ print("""OOPS.\n
It looks like Google Scholar changed their URL format or their output format.
-I went to count the cites for a fictitious paper, and found some."""
+I went to count the cites for a fictitious paper, and found some.""")
sys.exit(1)
def urlIsUseless(u):
@@ -182,7 +182,7 @@ if __name__ == '__main__':
bib = BibTeX.parseFile(config.MASTER_BIB)
remove_old()
- print "Downloading missing ranks."
+ print("Downloading missing ranks.")
for ent in bib.entries:
getCite(ent['title'], cache=True, update=True)
@@ -190,13 +190,13 @@ if __name__ == '__main__':
for ent in bib.entries:
haveOne = False
for utype in URLTYPES:
- if ent.has_key("www_%s_url"%utype):
+ if "www_%s_url"%utype in ent:
haveOne = True
break
if haveOne:
continue
- print ent.key, "has no URLs given."
+ print((ent.key, "has no URLs given."))
urls = [ u for u in getPaperURLs(ent['title']) if not urlIsUseless(u) ]
for u in urls:
- print "\t", u
+ print(("\t", u))
diff --git a/writeHTML.py b/writeHTML.py
@@ -1,12 +1,13 @@
-#!/usr/bin/python2
+#!/usr/bin/python3
# Copyright 2003-2008, Nick Mathewson. See LICENSE for licensing info.
# Copyright 2018, 2019 ng0 <ng0@n0.is>
"""
Generate indices by author, topic, date, and BibTeX key.
"""
-from __future__ import print_function
+
from future.utils import raise_with_traceback
+from io import BytesIO ## for Python 3
import sys
import re
import os
@@ -16,7 +17,7 @@ import config
assert sys.version_info[:3] >= (2, 2, 0)
-os.umask(022)
+os.umask(0o22)
def getTemplate(name):
template_file = open(name)
@@ -81,7 +82,7 @@ def writeHTML(f, sections, sectionType, fieldName, choices,
#
tagListStr = []
- st = config.TAG_SHORT_TITLES.keys()
+ st = list(config.TAG_SHORT_TITLES.keys())
st.sort()
root = "../"*pathLength(config.TAG_DIRECTORIES[tag])
if root == "": root = "."
@@ -144,7 +145,7 @@ def writePageSet(config, bib, tag):
cache_url_path = BibTeX.smartJoin("../"*pathLength(tagdir),
config.CACHE_DIR)
if not os.path.exists(outdir):
- os.makedirs(outdir, 0755)
+ os.makedirs(outdir, 0o755)
##### Sorted views:
## By topic.
@@ -186,7 +187,7 @@ def writePageSet(config, bib, tag):
except ValueError:
last_year = int(entries[-2][1][0].get('year'))
- years = map(str, range(first_year, last_year+1))
+ years = list(map(str, list(range(first_year, last_year+1))))
if entries[-1][0] == 'Unknown':
years.append("Unknown")
@@ -252,7 +253,7 @@ def writePageSet(config, bib, tag):
for ent in entries:
bib_file_dir = os.path.join(biboutdir, ent.key)
if not os.path.exists(bib_file_dir):
- os.makedirs(bib_file_dir, 0755)
+ os.makedirs(bib_file_dir, 0o755)
single_bib_file = open(os.path.join(bib_file_dir,
"record.bib"),
'w')
@@ -270,5 +271,5 @@ if __name__ == '__main__':
bib = BibTeX.parseFile(config.MASTER_BIB)
- for tag in config.TAG_DIRECTORIES.keys():
+ for tag in list(config.TAG_DIRECTORIES.keys()):
writePageSet(config, bib, tag)
