import csv
from collections import Counter
import SonicScrewdriver as utils
ficids = set()
meta = dict()
ficsource = "/Volumes/TARDIS/work/fiction/metadata/fiction_metadata.csv"
with open(ficsource, encoding="utf-8") as f:
reader = csv.DictReader(f)
fieldnames = reader.fieldnames
for row in reader:
htid = row["htid"]
dirtyhtid = utils.dirty_pairtree(htid)
ficids.add(dirtyhtid)
meta[dirtyhtid] = row
metasource = "/Volumes/TARDIS/work/metadata/MergedMonographs.tsv"
mysterysubjects = Counter()
scifisubjects = Counter()
gothsubjects = Counter()
gothclues = ["ghost stories", "gothic revival", "horror"]
genretags = dict()
def add_tag(genretags, htid, tagtoadd):
if htid not in genretags:
genretags[htid] = set()
# getidstoadd
import SonicScrewdriver as utils
import os
with open('/Users/tunder/Dropbox/GenreProject/python/granger/correctedmeta.tsv', encoding = 'utf-8') as f:
filelines = f.readlines()
ids2get = [x.split('\t')[0] for x in filelines]
fileswehave = os.listdir('/Users/tunder/Dropbox/GenreProject/python/granger/elite/')
idswehave = set([x.replace('.poe.tsv','') for x in fileswehave if x.endswith('.poe.tsv')])
with open('/Users/tunder/Dropbox/GenreProject/python/granger/ids2get.tsv', mode = 'w', encoding = 'utf-8') as f:
for anid in ids2get:
if anid not in idswehave and utils.clean_pairtree(anid) not in idswehave:
f.write(utils.dirty_pairtree(anid) + '\n')
if thisreader not in readerowners[f]:
readerowners[f].append(thisreader)
paths[f].append(thispath)
print(len(tagset))
allfiles = tagset
# This is a list of all the filenames (note, filenames not docids)
# that we found in the /readers sourcedir.
train1 = pd.read_csv('../bzipmeta.csv', dtype = 'object', index_col = 'docid')
tidx = set(train1.index.values)
for filename in allfiles:
docid = filename.replace('.csv', '')
if utils.dirty_pairtree(docid) not in tidx:
print(docid)
genrestocheck = ['fic', 'poe']
equivalences = {'non', 'bio', 'other'}
volumesingenre = dict()
for g in genrestocheck:
volumesingenre[g] = []
alldocids = set()
for filename, owners in readerowners.items():
path = paths[filename][0]
if 'metadat' in filename:
print(filename)
import SonicScrewdriver as utils
with open('/Users/tunder/Dropbox/GenreProject/metadata/getficids1899.txt', encoding = 'utf-8') as f:
ids = [x.rstrip() for x in f.readlines()]
newids = list()
for anid in ids:
newid = utils.dirty_pairtree(anid)
newids.append(newid)
with open('/Users/tunder/Dropbox/GenreProject/metadata/dirtyficids1899.txt', mode = 'w', encoding = 'utf-8') as f:
for anid in newids:
f.write(anid + '\n')
if thisreader not in readerowners[f]:
readerowners[f].append(thisreader)
paths[f].append(thispath)
print(len(tagset))
allfiles = tagset
# This is a list of all the filenames (note, filenames not docids)
# that we found in the /readers sourcedir.
train1 = pd.read_csv('bzipmeta.csv', dtype = 'object', index_col = 'docid')
tidx = set(train1.index.values)
for filename in allfiles:
docid = filename.replace('.csv', '')
if utils.dirty_pairtree(docid) not in tidx:
print(docid)
genrestocheck = ['fic', 'poe', 'dra', 'bio', 'non']
equivalences = {'non', 'bio', 'other'}
volumesingenre = dict()
for g in genrestocheck:
volumesingenre[g] = []
alldocids = set()
errorconditions = dict()
erroramounts = dict()
errorids = []
percentagesbydoc = dict()
docidstoget = set()
with open(metafile, encoding='utf-8') as f:
reader = csv.DictReader(f)
for row in reader:
tagset = utils.get_tagset(row['genretags'])
if 'drop' in tagset:
continue
getthis = False
for tag in tagstoget:
if tag in tagset:
getthis = True
if getthis:
docidstoget.add(row['docid'])
filespresent = os.listdir('/Users/tunder/Dropbox/fiction/data/')
docidspresent = set([
x.replace('.fic.tsv', '') for x in filespresent if x.endswith('.fic.tsv')
])
docidsneeded = docidstoget - docidspresent
outfile = '/Users/tunder/Dropbox/fiction/meta/filestoget' + str(
datetime.date.today()) + '.txt'
with open(outfile, mode='w', encoding='utf-8') as f:
for docid in docidsneeded:
outid = utils.dirty_pairtree(docid)
f.write(outid + '\n')
import SonicScrewdriver as utils
with open('/Users/tunder/Dropbox/GenreProject/metadata/getficids1899.txt',
encoding='utf-8') as f:
ids = [x.rstrip() for x in f.readlines()]
newids = list()
for anid in ids:
newid = utils.dirty_pairtree(anid)
newids.append(newid)
with open('/Users/tunder/Dropbox/GenreProject/metadata/dirtyficids1899.txt',
mode='w',
encoding='utf-8') as f:
for anid in newids:
f.write(anid + '\n')
# organize_anovaset.py
import SonicScrewdriver as utils
import csv
rows, columns, table = utils.readtsv('/Volumes/TARDIS/work/metadata/MergedMonographs.tsv')
with open('anovaset.tsv', encoding = 'utf-8') as f:
filelines = f.readlines()
anovaset = list()
for line in filelines:
fields = line.split('\t')
htid = utils.dirty_pairtree(fields[0])
category = fields[1]
if category == 'elite':
category = 'reviewed'
elif category == 'vulgar':
category = 'random'
if htid in rows:
author = table['author'][htid]
title = table['title'][htid]
date = utils.simple_date(htid, table)
imprint = table['imprint'][htid]
enumcron = table['enumcron'][htid]
anovaset.append([htid, category, date, enumcron, author, title, imprint])
with open('anovaset.csv', mode='w', encoding = 'utf-8') as f:
writer = csv.writer(f)
import SonicScrewdriver as utils
metapath = '/Users/tunder/Dropbox/GenreProject/metadata/richpoemeta1859.tsv'
with open(metapath, encoding = 'utf-8') as f:
filelines = f.readlines()
getpoe = [x.split('\t')[0] for x in filelines]
outpath = '/Users/tunder/Dropbox/GenreProject/python/reception/getpoe.txt'
with open(outpath, mode = 'w', encoding = 'utf-8') as f:
for htid in getpoe:
htid = utils.dirty_pairtree(htid)
f.write(htid + '\n')
# getidstoadd
import SonicScrewdriver as utils
import os
with open(
'/Users/tunder/Dropbox/GenreProject/python/granger/correctedmeta.tsv',
encoding='utf-8') as f:
filelines = f.readlines()
ids2get = [x.split('\t')[0] for x in filelines]
fileswehave = os.listdir(
'/Users/tunder/Dropbox/GenreProject/python/granger/elite/')
idswehave = set(
[x.replace('.poe.tsv', '') for x in fileswehave if x.endswith('.poe.tsv')])
with open('/Users/tunder/Dropbox/GenreProject/python/granger/ids2get.tsv',
mode='w',
encoding='utf-8') as f:
for anid in ids2get:
if anid not in idswehave and utils.clean_pairtree(
anid) not in idswehave:
f.write(utils.dirty_pairtree(anid) + '\n')
with open(metafile, encoding = 'utf-8') as f:
reader = csv.DictReader(f)
for row in reader:
tagset = utils.get_tagset(row['genretags'])
if 'drop' in tagset:
continue
getthis = False
for tag in tagstoget:
if tag in tagset:
getthis = True
if getthis:
docidstoget.add(row['docid'])
filespresent = os.listdir('/Users/tunder/Dropbox/fiction/data/')
docidspresent = set([x.replace('.fic.tsv', '') for x in filespresent if x.endswith('.fic.tsv')])
docidsneeded = docidstoget - docidspresent
outfile = '/Users/tunder/Dropbox/fiction/meta/filestoget' + str(datetime.date.today()) + '.txt'
with open(outfile, mode = 'w', encoding = 'utf-8') as f:
for docid in docidsneeded:
outid = utils.dirty_pairtree(docid)
f.write(outid + '\n')
prefix = parts[0]
pages = []
for i in range(0, maxpage + 1):
filename = prefix + '/' + str(i) + '.txt'
thispage = tar.extractfile(filename)
page = [x.decode('utf-8') for x in thispage.readlines()]
pages.append(page)
pagelist, removed = header.remove_headers(pages, romannumerals)
outpath = outfolder + afile
outpath = outpath.replace('.tar', '.txt')
with open(outpath, mode='w', encoding='utf-8') as f:
for idx, page in enumerate(pagelist):
f.write('\n<#PG# ' + str(idx) + '>\n')
for line in page:
f.write(line)
theid = utils.dirty_pairtree(afile.replace('.tar', ''))
alltheids.append(theid)
# with open(outfolder + 'nonfictionmetadata.csv', mode = 'w', encoding = 'utf-8') as f:
# writer = csv.DictWriter(f, fieldnames = fieldnames)
# writer.writeheader()
# for anid in alltheids:
# row = metadict[anid]
# writer.writerow(row)
