mtholder

#!/usr/bin/env python
import sys
from peyotl.api.taxomachine import Taxomachine
taxomachine = Taxomachine()
from peyotl.nexson_syntax import write_as_json
context_name = 'All life'
for n in sys.argv[1:]:
    if n.startswith('-c'):
        context_name = n[2:]
    else:

mtholder

#!/usr/bin/env python
import sys
from peyotl.api.taxomachine import Taxomachine
taxomachine = Taxomachine()
from peyotl.nexson_syntax import write_as_json
context_name = 'All life'
for n in sys.argv[1:]:
    if n.startswith('-c'):
        context_name = n[2:]
    else:

mtholder

#!/usr/bin/env python
import sys
import os
import re
_SCRIPT_NAME = os.path.split(sys.argv[0])[-1]
_FORBIDDEN = re.compile(r'[^- 0-9a-zA-Z`~@#$%^&*()_+={}|\\\[\]:;"\'<,>.?/]')
_NEEDS_QU_PUNC_STR = r'[\[\]():,;]'
_NEEDS_QUOTES_PATTERN = re.compile(r'(\s|' + _NEEDS_QU_PUNC_STR + ')')
_NEEDS_QUOTES_PUNC_PATTERN = re.compile(_NEEDS_QU_PUNC_STR)
_SINGLE_QUOTE = "'"

mtholder

#!/usr/bin/env python
# vim: set fileencoding=utf-8 :
import sys
import os
import re
u'''
Unicode char lists found by running against ott2.8
Using the names column in taxonomy.tsv required allowing the 
following unicode characters:
    æ denoted: u'\xe6'

mtholder

#!/bin/bash
if ! which ott_names_to_newick.py >/dev/null 2>&1
then 
    echo 'Download ott_names_to_newick.py from https://gist.github.com/mtholder/ac58ab1b3c6a962b9bdc and put it on your PATH'
    exit 1
fi
echo 'grabbing names from taxonomy'
set -x
awk 'BEGIN { FS = "\t\\|\t" } ; {print $3 }' taxonomy.tsv >names.txt
awk 'BEGIN { FS = "\t\\|\t" } ; {print $6 }' taxonomy.tsv >uniqnames.txt

mtholder

#!/usr/bin/env python
import codecs
import sys
chars = set()
for filepath in sys.argv[1:]:
    with codecs.open(filepath, 'r', encoding='utf-8') as fo:
        for line in fo:
            chars.update(iter(line))
c = list(chars)
c.sort()

mtholder

/* Most of this code is from GBParsy which available from https://code.google.com/p/gbfp/

T.-H. Lee, Y.-K. Kim and B.H. Nahm (2008) GBParsy: A GenBank flatfile parser library with high speed. BMC Bioinformatics, 9:321.

That code is released under the GPL (see bottom of file).


Mark T. Holder only wrote the slight modification to parsing of the GI and a simpliefied main 
function (based on the example seqext.c from gbfpy)

mtholder

#!/usr/bin/env python
from StringIO import StringIO
import sys

out = sys.stdout
def get_indented(x, indent):
    start_indent = indent
    written_something = False
    out = StringIO()
    for letter in x:

mtholder

#!/usr/bin/env python
from dendropy import DnaCharacterMatrix, Tree
import sys
d = DnaCharacterMatrix.get(path=sys.argv[1],
                           schema='fasta')
# make the taxon_namespace immutable, so the tree does not add
#   new labels...
d.taxon_namespace.is_mutable = False
tree = Tree.get(path=sys.argv[2],
                schema='newick',

mtholder

#!/usr/bin/env python
import sys
import re

inp = sys.stdin
outp = sys.stdout

JS_PAT = re.compile(r'^<script src="/opentree/static/(.+)" type="text/javascript"></script>\s+$')
CSS_PAT = re.compile(r'^<link href="/opentree/static/(.+)" rel="stylesheet" type="text/css" />\s+$')