langner

"""Transformation of trees into Prufer sequence and back.

The Prufer sequence of a labeled tree is a unique seqience associated
with that tree on length n-2 where there are n vertices in the tree.
More information: https://en.wikipedia.org/wiki/Prüfer_sequence

Copyright 2015 Karol M. Langner, Google Inc.
Licensed under the Apache License, Version 2.0
http://www.apache.org/licenses/LICENSE-2.0
"""

langner

def similar_first_author(author1, author2):
    """Determine whether two first authors have the same names.

    Since there can be various fluctuations in first names and initials, we will
    only check the first word in the author string and the first letter of the
    second word. Although the second word is usually the first name, there will
    be exceptions for multi-word last names, but this will be a small minority
    and still passes our test. In case there is just a single word, use just that.
    """
    author1 = author1.lower().decode('utf-8')

langner

greek_alphabet = {
    u'\u0391': 'Alpha',
    u'\u0392': 'Beta',
    u'\u0393': 'Gamma',
    u'\u0394': 'Delta',
    u'\u0395': 'Epsilon',
    u'\u0396': 'Zeta',
    u'\u0397': 'Eta',
    u'\u0398': 'Theta',
    u'\u0399': 'Iota',

langner

aptitude purge `aptitude search ~c | awk '{ print $2 }'`

langner

#!/bin/bash

# Create work directory and empty it.
ROOTDIR="postgresql-namedatalen"
mkdir -p $ROOTDIR
cd $ROOTDIR
rm -rf *

# Get the sources and determine current version.
PKGNAME="postgresql-9.1"

langner

Index: postgresql-9.1-9.1.14/src/include/pg_config_manual.h
===================================================================
--- postgresql-9.1-9.1.14.orig/src/include/pg_config_manual.h   2014-10-14 16:55:38.000000000 -0400
+++ postgresql-9.1-9.1.14/src/include/pg_config_manual.h        2014-10-14 16:56:01.598940653 -0400
@@ -17,7 +17,7 @@
  *
  * Changing this requires an initdb.
  */
-#define NAMEDATALEN 64
+#define NAMEDATALEN 256

langner

import cclib
import numpy
import urllib

def nuclear_repulsion_energy(data):
    nre = 0.0
    for i in range(data.natom):
        ri = data.atomcoords[0][i]
        zi = data.atomnos[i]
        for j in range(i+1, data.natom):

langner

# amavis messages
amavis\[[0-9]+\]: \([-0-9]+\) Passed (CLEAN|BAD-HEADER|SPAM|BANNED)

# avahi daemon: warnings about invalid repsonses and such
avahi-daemon\[[0-9]+\]: Invalid (query packet|legacy unicast query packet|response packet from host)
avahi-daemon\[[0-9]+\]: Received response from host [.0-9]+ with invalid source port [0-9]+ on interface         
avahi-daemon\[[0-9]+\]:( last)? message repeated [0-9]+ times
avahi-daemon\[[0-9]+\]: server.c: Packet too short or invalid while reading response record.
avahi-daemon\[[0-9]+\]: dbus-protocol.c: Too many objects for client

langner

import difflib
import string

def similar_titles(t1, t2, accuracy=1.00, debug=None):
    """Determine whether two titles are similar.

    As a rule, we want titles to be identical after removing whitespace
    and punctuation. Other discrepancies should be dealt with manually by
    ensuring the titles are correct, or by replacing strings in all titles,
    in this function, before comparing them.

langner

def similar_pages(pages1, pages2):
    """Determine whether two pages strings are similar.

    Redundant digits in the end page should be ignored -- for example, 1660-1661 can be
    reduced to 1660-1 -- and the end page (and hyphen) can be skipped if it's a single page.
    Additionally, for some journals, WoK can also replace the end page with something else,
    for example: 241-+ instead of 241-247.e9 (supp info), or O1125-U144 (no idea what that is),
    and they have said this cannot change for technical reasons. Oh well.

    Additional exceptions: