vphill

United States - Oklahoma - Oklahoma County - Oklahoma City	35.467560	-97.516430
United States - Texas - Dallas County - Dallas	32.783060	-96.806670
United States - Texas	31.250440	-99.250610
United States	39.760000	-98.500000
United States - Texas - Tarrant County - Fort Worth	32.725410	-97.320850
United States - Texas - Denton County - Denton	33.214840	-97.133070
United States - Texas - Bexar County - San Antonio	29.424120	-98.493630
United States - Texas - Taylor County - Abilene	32.448740	-99.733140
United States - Oklahoma - Cleveland County - Norman	35.222570	-97.439480
United States - Texas - Harris County - Houston	29.763280	-95.363270

vphill

"""untl_breaker script for processing OAI-PMH 2.0 Repository XML Files"""

import argparse
import sys
from xml.etree import ElementTree
import csv


UNTL_NAMESPACE = "{http://digital2.library.unt.edu/untl/}"
UNTL_NSMAP = {"untl": UNTL_NAMESPACE}

vphill

File used for captions. https://texashistory.unt.edu/ark:/67531/metapth845109/

File length = 00:15:50.52

Computer	Device	Model	Time
libcpt01	CPU	medium	16m11s
libcpt01	NVIDIA GeForce GTX 1080 8GB	small.en	1m24s
libcpt01	NVIDIA GeForce GTX 1080 8GB	medium	4m35s
libcpt10	NVIDIA GeForce GTX 1080 8GB	large	N/A

vphill

"""script for converting NOVAXCHANGE tape files into record block files"""

import sys


def iterate_stream(stream, delimiter, max_read_size=1024 * 4):
    """ Reads `delimiter` separated strings or bytes from `stream`. """
    empty = '' if isinstance(delimiter, str) else b''
    chunks = []
    delimiter_len = len(delimiter)

vphill

00000000  50 00 56 4f 4c 31 30 32  38 30 30 32 20 20 20 20  |P.VOL1028002    |
00000010  20 20 20 20 20 20 20 20  20 20 20 20 20 20 20 20  |                |
*
00000050  20 31 50 00 50 00 48 44  52 31 30 32 38 30 30 32  | 1P.P.HDR1028002|
00000060  2d 30 30 30 30 30 30 30  30 30 30 30 32 38 30 30  |-000000000002800|
00000070  32 30 30 30 31 30 30 30  31 30 30 30 31 30 30 30  |2000100010001000|
00000080  30 35 30 30 36 20 30 30  30 30 30 20 30 30 30 30  |05006 00000 0000|
00000090  30 30 4e 4f 56 41 58 43  48 41 4e 47 45 20 20 20  |00NOVAXCHANGE   |
000000a0  20 20 20 20 20 20 50 00  50 00 48 44 52 32 46 31  |      P.P.HDR2F1|
000000b0  36 33 38 34 30 34 30 39  36 20 30 20 20 20 20 20  |638404096 0     |

vphill

00000000  50 00 56 4f 4c 31 30 32  38 30 30 30 20 20 20 20  |P.VOL1028000    |
00000010  20 20 20 20 20 20 20 20  20 20 20 20 20 20 20 20  |                |
*
00000050  20 31 50 00 50 00 48 44  52 31 30 32 38 30 30 30  | 1P.P.HDR1028000|
00000060  2d 30 30 30 30 30 30 30  30 30 30 30 32 38 30 30  |-000000000002800|
00000070  30 30 30 30 31 30 30 30  31 30 30 30 31 30 30 30  |0000100010001000|
00000080  30 35 30 30 36 20 30 30  30 30 30 20 30 30 30 30  |05006 00000 0000|
00000090  30 30 4e 4f 56 41 58 43  48 41 4e 47 45 20 20 20  |00NOVAXCHANGE   |
000000a0  20 20 20 20 20 20 50 00  50 00 48 44 52 32 46 31  |      P.P.HDR2F1|
000000b0  36 33 38 34 30 34 30 39  36 20 30 20 20 20 20 20  |638404096 0     |

vphill

Keybase proof

I hereby claim:

• I am vphill on github.
• I am vphill (https://keybase.io/vphill) on keybase.
• I have a public key ASDhDNBIIwjmaMYPtjU37t9hgxZV5HBAjpZjmN8b0LGM6Ao

To claim this, I am signing this object:

vphill

mapping = {
        'ATT-': 'ADJ',
        '==LOC': 'ADP',
        '-ADV': 'ADV',
        'adv': 'ADV',
        'ADVR': 'ADV',
        '==DDET': 'DET',
        'interj': 'INTJ',
        'n': 'NOUN',
        'n:Any': 'NOUN',

vphill

   1  -APX
   1  -BE
   1  -INTEND
   1  -NES
   1  -PROHB
   1  -SOLCT
   1  -SUP
   1  ==CTE
   1  =INT
   1  =pdet

vphill

def lemmatize(token_list):
    """very simple implementation"""

    out_tokens = []

    for t in token_list:
        if t.endswith('ies'):
            t = t[:-3] + 'y'
        elif t.endswith("'s"):
            t = t[:-2]