def processAtharCorpus(infiles, outfile):
"""
Loads the Athar .html corpus into a JSON file of contexts
Args:
infiles: file mask of HTML files to load
outfile: name of .json file to write to
"""
import glob
cp.useLocalCorpus()
cp.Corpus.connectCorpus("g:\\nlp\\phd\\aac")
reader=AtharCorpusReader()
all_contexts=[]
all_docs=[]
for f in glob.glob(infiles):
print("Loading ",f)
docs,contexts=reader.readFile(f)
all_contexts.extend(contexts)
all_docs.extend(docs)
doc_dict={}
for doc in all_docs:
doc_dict[doc.metadata["guid"]]=doc.data
json.dump(doc_dict,file(outfile,"w"))
def main():
drive="g"
cp.useLocalCorpus()
cp.Corpus.connectCorpus(drive+":\\nlp\\phd\\pmc")
debugging_files=[
r"articles.I-N\J_Contemp_Brachytherapy\J_Contemp_Brachytherapy_2012_Sep_29_4(3)_176-181.nxml",
r"articles.O-Z\PLoS_ONE\PLoS_One_2013_Dec_20_8(12)_e85076.nxml",
r"articles.C-H\Gastroenterol_Rep_(Oxf)\Gastroenterol_Rep_(Oxf)_2013_Sep_17_1(2)_149-152.nxml",
]
## debugging_files=cp.Corpus.selectRandomInputFiles(500,"*.nxml")
## generateSideBySide(debugging_files)
## inspectFiles(debugging_files)
pass
def main():
import minerva.db.corpora as cp
drive="g"
cp.useLocalCorpus()
cp.Corpus.connectCorpus(drive+":\\nlp\\phd\\pmc_coresc\\")
import read_jatsxml
debugging_files=[
r"data\scratch\mpx245\epmc\output\Out_PMC3184115_PMC3205799.xml.gz.gz\3187739_annotated.xml",
## r"Out_PMC549041_PMC1240567.xml.gz.gz\555959_done.xml",
## r"Out_PMC549041_PMC1240567.xml.gz.gz\555763_done.xml",
]
read_jatsxml.generateSideBySide(debugging_files)
pass
def basicTest():
print (__file__)
import minerva.db.corpora as cp
drive="g"
cp.useLocalCorpus()
cp.Corpus.connectCorpus(drive+":\\nlp\\phd\\pmc")
from minerva.proc.general_utils import loadFileText
from minerva.scidoc.xmlformats.read_jatsxml import JATSXMLReader
reader = JATSXMLReader()
doc=reader.read(loadFileText(r"G:\NLP\PhD\pmc\inputXML\articles.O-Z\PLoS_ONE\\PLoS_One_2013_Dec_20_8(12)_e85076.nxml"),"one")
## renderer=CSLRenderer(doc,".." + os.sep + "cit_styles" + os.sep + 'ama.csl')
renderer=CSLRenderer(doc,"ama")
print("Citations\n\n")
for cit in doc.citations:
print(renderer.getCitationText(cit))
print("Bibliography\n\n")
for line in renderer.getBibliography():
print(line)