Spaces:
No application file
No application file
File size: 6,000 Bytes
b7731cd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 |
# Copyright 1999 by Jeffrey Chang. All rights reserved.
#
# This file is part of the Biopython distribution and governed by your
# choice of the "Biopython License Agreement" or the "BSD 3-Clause License".
# Please see the LICENSE file that should have been included as part of this
# package.
"""Code to work with Medline from the NCBI.
Classes:
- Record A dictionary holding Medline data.
Functions:
- read Reads one Medline record
- parse Allows you to iterate over a bunch of Medline records
"""
class Record(dict):
"""A dictionary holding information from a Medline record.
All data are stored under the mnemonic appearing in the Medline
file. These mnemonics have the following interpretations:
========= ==============================
Mnemonic Description
--------- ------------------------------
AB Abstract
CI Copyright Information
AD Affiliation
IRAD Investigator Affiliation
AID Article Identifier
AU Author
FAU Full Author
CN Corporate Author
DCOM Date Completed
DA Date Created
LR Date Last Revised
DEP Date of Electronic Publication
DP Date of Publication
EDAT Entrez Date
GS Gene Symbol
GN General Note
GR Grant Number
IR Investigator Name
FIR Full Investigator Name
IS ISSN
IP Issue
TA Journal Title Abbreviation
JT Journal Title
LA Language
LID Location Identifier
MID Manuscript Identifier
MHDA MeSH Date
MH MeSH Terms
JID NLM Unique ID
RF Number of References
OAB Other Abstract
OCI Other Copyright Information
OID Other ID
OT Other Term
OTO Other Term Owner
OWN Owner
PG Pagination
PS Personal Name as Subject
FPS Full Personal Name as Subject
PL Place of Publication
PHST Publication History Status
PST Publication Status
PT Publication Type
PUBM Publishing Model
PMC PubMed Central Identifier
PMID PubMed Unique Identifier
RN Registry Number/EC Number
NM Substance Name
SI Secondary Source ID
SO Source
SFM Space Flight Mission
STAT Status
SB Subset
TI Title
TT Transliterated Title
VI Volume
CON Comment on
CIN Comment in
EIN Erratum in
EFR Erratum for
CRI Corrected and Republished in
CRF Corrected and Republished from
PRIN Partial retraction in
PROF Partial retraction of
RPI Republished in
RPF Republished from
RIN Retraction in
ROF Retraction of
UIN Update in
UOF Update of
SPIN Summary for patients in
ORI Original report in
========= ==============================
"""
def parse(handle):
"""Read Medline records one by one from the handle.
The handle is either is a Medline file, a file-like object, or a list
of lines describing one or more Medline records.
Typical usage::
>>> from Bio import Medline
>>> with open("Medline/pubmed_result2.txt") as handle:
... records = Medline.parse(handle)
... for record in records:
... print(record['TI'])
...
A high level interface to SCOP and ASTRAL ...
GenomeDiagram: a python package for the visualization of ...
Open source clustering software.
PDB file parser and structure class implemented in Python.
"""
# These keys point to string values
textkeys = (
"ID",
"PMID",
"SO",
"RF",
"NI",
"JC",
"TA",
"IS",
"CY",
"TT",
"CA",
"IP",
"VI",
"DP",
"YR",
"PG",
"LID",
"DA",
"LR",
"OWN",
"STAT",
"DCOM",
"PUBM",
"DEP",
"PL",
"JID",
"SB",
"PMC",
"EDAT",
"MHDA",
"PST",
"AB",
"EA",
"TI",
"JT",
)
handle = iter(handle)
key = ""
record = Record()
for line in handle:
line = line.rstrip()
if line[:6] == " ": # continuation line
if key in ["MH", "AD"]:
# Multi-line MESH term, want to append to last entry in list
record[key][-1] += line[5:] # including space using line[5:]
else:
record[key].append(line[6:])
elif line:
key = line[:4].rstrip()
if key not in record:
record[key] = []
record[key].append(line[6:])
elif record:
# Join each list of strings into one string.
for key in record:
if key in textkeys:
record[key] = " ".join(record[key])
yield record
record = Record()
if record: # catch last one
for key in record:
if key in textkeys:
record[key] = " ".join(record[key])
yield record
def read(handle):
"""Read a single Medline record from the handle.
The handle is either is a Medline file, a file-like object, or a list
of lines describing a Medline record.
Typical usage:
>>> from Bio import Medline
>>> with open("Medline/pubmed_result1.txt") as handle:
... record = Medline.read(handle)
... print(record['TI'])
...
The Bio* toolkits--a brief overview.
"""
records = parse(handle)
return next(records)
if __name__ == "__main__":
from Bio._utils import run_doctest
run_doctest()
|