class Merge(Debuggable):
"""
Standalone Processing object which merges current JATS/BITS XML file in to the Body of a BITS-XML document.
"""
def __init__(self):
self.args = self.read_command_line()
self.debug = Debug()
self.settings = Settings(self.args)
self.gv = GV(self.settings)
self.dr = self.args.get('<path>')
self.f = self.args.get('<input_file>')
self.scheme = self.args.get('<scheme>')
self.set_numbering_tags = self.args.get('--set-numbering-tags')
self.tr = etree.parse(os.path.join(self.dr, self.f))
Debuggable.__init__(self, 'Main')
if self.args.get('--debug'):
self.debug.enable_debug()
@staticmethod
def read_command_line():
"""
Reads and generates a docopt dictionary from the command line parameters.
Returns
-------
docopt : dictionary
A dictionary, where keys are names of command-line elements such as and values are theparsed values of those
elements.
"""
return docopt(__doc__, version='xmlMerge 0.0.1')
def create_output_bits(self):
"""
Create bits output file, generates a new file, if no file is found.
Otherwise the current file is appended to the book body as a book-part.
See Also
--------
create_book_part_bits, create_book_bits, do_file_io
"""
fuf = os.path.join(self.dr, self.gv.uuid)
pt = os.path.join(self.dr, os.path.basename(self.gv.uuid))
trf = None
if os.path.isfile(fuf):
trf = etree.parse(fuf)
bp = trf.find(".//book-body")
book_part = self.create_book_part_bits()
bp.append(book_part)
else:
trf = self.create_book_bits()
trf = self.process(trf)
self.do_file_io(
etree.tostring(trf,
pretty_print=False,
xml_declaration=True,
encoding='UTF-8',
standalone='yes'), 'w', pt)
def create_output_jats(self):
"""
Create jats output file, generates a new file,
See Also
--------
create_book_part_bits, create_book_bits, do_file_io
"""
fuf = os.path.join(self.dr, self.gv.uuid)
pt = os.path.join(self.dr, os.path.basename(self.gv.uuid))
trf = None
if os.path.isfile(fuf):
trf = etree.parse(fuf)
bpf = trf.find(".//body")
f, bd, bk = self.get_xml_parts()
if bd is not None:
for sec in list(bd):
bpf.append(sec)
bkrf = trf.find(".//back/ref-list")
for r in bk.findall('.//ref-list/ref'):
bkrf.append(r)
bkff = trf.find(".//back/fn-group")
for fn in bk.findall('.//fn-group/fn'):
bkff.append(fn)
else:
trf = self.create_journal_jats()
trf = self.process(trf)
self.do_file_io(
etree.tostring(trf,
pretty_print=False,
xml_declaration=True,
encoding='UTF-8',
standalone='yes'), 'w', pt)
def process(self, tr):
"""
Process BITS-XML file and do all transformations into the elementtree
Parameters
----------
tr : elementtree
element tree as input
Returns
-------
tr : elementtree
transformed element tree
See Also
--------
globals.set_numbering_tags(), set_book_part_attributes()
"""
tr = self.gv.set_numbering_tags(self.set_numbering_tags.split(','),
tr) if self.set_numbering_tags else tr
self.set_book_part_attributes(tr)
return tr
def set_book_part_attributes(self, tr):
"""
Add specific attributes to book-part
Parameters
----------
tr : elementtree
element tree as input
Returns
-------
tr : elementtree
transformed element tree
"""
book_parts = tr.findall('.//book-part')
for i, b in enumerate(book_parts):
b.attrib['id'] = "ch_" + str(i)
b.attrib['book-part-type'] = "chapter"
return tr
def create_metadata_path(self, metadata):
"""
creates the correct folder path for the metadata file. Metadata files should be in a folder : metadata
Parameters
----------
metadata : str
Suffix of the metadata files
Returns
-------
pth : str
Correct path of the metadata file in the folder structure
Notes
-----
We assume that metadata files are stored in a sub-folder named metadata
"""
p = os.path.dirname(self.f).split(os.sep)
del p[-4:]
name, ext = os.path.splitext(os.path.basename(self.gv.uuid))
file_name = [name, '.', metadata, '.', 'xml']
p.append('metadata')
p.append(''.join(file_name))
pth = os.sep.join(p)
self.debug.print_debug(self, 'merging headers' + str(pth))
return pth
def get_module_name(self):
"""
Reads the name of the module for debugging and logging
Returns
-------
name string
Name of the Module
"""
name = 'merge'
return name
def create_book_bits(self):
"""
creates a full BITS XML book and optionally adds metadata
Returns
-------
book : elementtree
Elementtree which complies to BITS XML Scheme.
See Also
---------
create_metadata_path, create_book_part_bits
"""
nsmap = {
'xlink': "http://www.w3.org/1999/xlink",
'mml': "http://www.w3.org/1998/Math/MathML",
"xml": "http://www.w3.org/XML/1998/namespace"
}
book = etree.Element(etree.QName('book'), nsmap=nsmap)
book.attrib['dtd-version'] = "2.1"
book.attrib[etree.QName(
'{http://www.w3.org/XML/1998/namespace}lang')] = "de"
book.attrib['book-type'] = "proceedings"
metadata = self.args.get('--metadata')
if metadata:
pth = self.create_metadata_path(metadata)
self.debug.print_console(self, 'merging headers' + str(pth))
if os.path.isfile(pth):
bp = etree.parse(pth).find('.//book-meta')
book.insert(0, bp)
else:
self.debug.print_console(
self, self.gv.PROJECT_INPUT_FILE_DOES_NOT_EXIST + str(pth))
#sys.exit(1)
else:
sys.exit('Metadata argument undefined')
bd = etree.Element("book-body")
bpbd = self.create_book_part_bits()
bd.append(bpbd)
book.append(bd)
return book
def create_journal_jats(self):
"""
creates a full JATS XML book and optionally adds metadata
Returns
-------
book : elementtree
Elementtree which complies to BITS XML Scheme.
See Also
---------
create_metadata_path, create_book_part_bits
"""
nsmap = {
'xlink': "http://www.w3.org/1999/xlink",
'mml': "http://www.w3.org/1998/Math/MathML",
"xml": "http://www.w3.org/XML/1998/namespace"
}
journal = etree.Element(etree.QName('article'), nsmap=nsmap)
journal.attrib['dtd-version'] = "3.0"
journal.attrib[etree.QName(
'{http://www.w3.org/XML/1998/namespace}lang')] = "de"
f, bd, bk = self.get_xml_parts()
metadata = self.args.get('--metadata')
if metadata:
pth = self.create_metadata_path(metadata)
if os.path.isfile(pth):
bpm = etree.parse(pth).find('.')
if bpm is not None:
if bpm.getroottree().getroot().tag == 'front':
journal.insert(0, bpm)
else:
self.debug.print_debug(self,
'front metadata unspecified')
sys.exit(1)
else:
journal.insert(0, f)
journal.append(bd)
if len(bk) > 0:
journal.append(bk)
else:
back = etree.Element(etree.QName('back'))
back.append(etree.Element(etree.QName('fn-group')))
back.append(etree.Element(etree.QName('ref-list')))
journal.append(back)
return journal
def create_book_part_bits(self):
"""
Reads a JATS XMl File and creates a book-part element tree according to BITS-XML.
Returns
-------
bp : elementtree
Book part elementTree
"""
f, bd, bk = self.get_xml_parts()
bp = etree.Element("book-part")
if f is not None:
if len(f):
bp.append(f)
if bd is not None:
bp.append(bd)
if bk is not None:
bp.append(bk)
return bp
def get_xml_parts(self):
"""
Returns the front-matter , body and back-matter of a JATS XML file in the above order
Returns
-------
f : elementtree
Front-matter of JATS elementTree
bd : elementtree
Body of JATS elementTree
bk : elementtree
Back-matter of JATS elementTree
"""
r = self.tr.getroot()
f = r.find(".//front")
if f is None:
f = r.find(".//book-part-meta")
bd = r.find(".//body")
bk = r.find(".//back")
return f, bd, bk
def do_file_io(self, s, mode, pth):
"""
Executes read or write operations on a path
Parameters
----------
s: str
Content to be written or None for read
mode: str
w for write , r for r
pth : str
Path to the file to be read or written
Raises
------
IOError
I/O operation fails
"""
try:
w = open(pth, mode)
if mode == 'w':
w.write(s.rstrip('\r\n'))
w.close()
if mode == 'r':
o = w.read()
w.close()
except IOError as i:
self.debug.print_debug(self, i)
print(i)
sys.exit(1)
def run(self):
"""
Runs the configuration on the processing object. Process JATS-XML file and merges it into the full BITS-XML file
See Also
--------
create_output_bits
Warning
-------
function create_output_jats not yet used
"""
self.gv.create_dirs_recursive(self.dr.split('/'))
if self.scheme == 'bits':
self.create_output_bits()
elif self.scheme == 'jats':
self.tr = self.create_output_jats()
class Prepare(Debuggable):
"""
Standalone Processing object to combine, clean and modify a JATS XML file and optionally inject BITS Metadata headers.
Features
--------
add Id numbering for any tag type, clean comments, remove unused references,
set numbering, add unique ids to certain tag types, sort references
"""
def __init__(self):
self.args = self.read_command_line()
self.debug = Debug()
self.settings = Settings(self.args)
self.gv = GV(self.settings)
Debuggable.__init__(self, 'Main')
if self.args.get('--debug'):
self.debug.enable_debug()
self.dr = self.args.get('<path>')
self.f = self.args.get('<input_file>')
self.stand_alone = self.args.get('--stand-alone')
self.tr = etree.parse(os.path.join(self.dr, self.f))
@staticmethod
def read_command_line():
"""
Reads and generates a docopt dictionary from the command line parameters.
Returns
-------
docopt : dictionary
A dictionary, where keys are names of command-line elements such as and values are theparsed values of those
elements.
"""
return docopt(__doc__, version='xml 0.1')
def citations_to_references(self):
""" Removes mixed-citation block, adds as a <sec> Section element
Returns
-------
tr : elementtree
"""
t = self.tr.getroot()
bd = t.find('.//body')
sc = etree.Element('sec')
ttl = etree.Element('title')
ttl.text = 'References'
sc.append(ttl)
mc = t.findall('.//mixed-citation')
if len(mc) > 0:
for r in mc:
r.tag = 'p'
sc.append(r)
bd.append(sc)
rlst = t.find('.//ref-list')
rlst.getparent().remove(rlst)
bck = t.find('.//back')
bck.append(etree.Element('ref-list'))
return self.tr
def clean_references(self):
""" removes references, which are not linked.
Parameters
-----------
tag : str
name of the XML tag
Returns
-------
tr : elementtree
See Also
--------
remove_element, remove_tags
"""
r = self.tr.getroot()
for e in r.findall('.//back/ref-list/ref'):
if e.attrib.get('id'):
if r.find(".//xref[@ref-type='bibr'][@rid='" +
e.attrib.get('id') + "']") is None:
self.remove_element(e)
else:
self.remove_element(e)
for e in r.findall(".//xref[@ref-type='bibr']"):
if r.find(".//back/ref-list/ref[@id='" + e.attrib.get('rid') +
"']") is None:
if e.getparent() is not None:
for c in e.getparent().getiterator():
if c.tag == 'xref' and c.attrib.get(
'ref-type') == 'bibr':
self.remove_tags(c)
return self.tr
def remove_tags(self, e):
"""
Takes an etree element and replaces it with its own text
Parameters
----------
e : element
Element to be replaced
"""
if e.getparent() is not None:
previous = e.getprevious()
if previous is not None:
if previous.tail:
if e.text:
previous.tail = previous.tail + e.text
if e.tail:
previous.tail = previous.tail + e.tail
e.getparent().remove(e)
def remove_element(self, e):
"""
Remove any element only if it has a parent
Parameters
----------
e : element
Element to be replaced
"""
if e.getparent() is not None:
e.getparent().remove(e)
def set_uuids_for_back_matter(self, tags):
"""
Add unique id tags to any of the sub-elements of the back matter
Parameters
----------
tags: list
list of elements
Returns
-------
tr : elementtree
"""
for s in tags:
f = {}
ref_type = 'bibr' if s == 'ref' else s
fns = self.tr.getroot().findall(''.join(
['.//xref/[@ref-type="', ref_type, '"]']))
for i in fns:
rid = ''.join(['bibd', str(uuid.uuid4())])
f[i.attrib['rid']] = rid
i.set('rid', rid)
for m in list(f.keys()):
n = self.tr.getroot().find(''.join(
['.//' + s + '/[@id="', m, '"]']))
if n is not None:
n.set('id', f[m]) if len(n) > 0 else ''
return self.tr
def set_numbering_values(self, tag, attr, value, count, range_list):
"""
Adds numerical values to a tag in arguments list
Parameters
---------
tag: str
xml tag name
attr: str
attribute name
value :str
value name
count : int
current sequence number
range_list : list
lower and upper level for the numbering
See Also
--------
set_roman_numbers
"""
searchTag = './/' + tag + '[@' + attr + '="' + value + '"]'
elems = self.tr.getroot().findall(searchTag)
range_count = 1
for elem in elems:
elem.text, range_count = self.set_roman_numbers(
count, range_count, range_list)
count += 1
return self.tr, count
def convert_int_to_roman(self, i):
"""
Converts an integer number into a roman number
Parameters
---------
i : int
integer number
Returns
-------
result : str
Roman number
"""
result = []
for integer, numeral in self.gv.numeral_map:
count = i // integer
result.append(numeral * count)
i -= integer * count
return ''.join(result)
def set_roman_numbers(self, count, r_count, range_list):
"""
Converts a given set of elements defined by range_array into roman numbers
Parameters
---------
count :int
r_count : int
range_list : list
lower and upper level for the numbering
Returns
-------
val : str
r_count: int
See Also
--------
convert_int_to_roman
"""
val = str(count)
if int(range_list[0]) <= count <= int(range_list[1]):
val = self.convert_int_to_roman(r_count).lower()
r_count += 1
else:
val = str(count - r_count + 1)
return val, r_count
def merge_metadata(self, metadata):
"""
reads a metadata file path and merge its content into the metadata section
Parameters
----------
metadata : str
suffix of the metadata files
Returns
-------
tr : elementTree
Element tree of the current file
See Also
-------
create_metadata_path
"""
r = self.tr.getroot()
pth = self.create_metadata_path(metadata)
if os.path.isfile(pth):
fr = r.find('.//front')
if len(fr):
bg = r.find('.//body').getparent()
fr.getparent().remove(fr)
bpm = etree.parse(pth).find('.//book-part-meta')
if bpm is None:
bpm = etree.parse(pth).find('.')
if bpm is not None:
if bpm.getroottree().getroot().tag == 'front':
bg.insert(0, bpm)
else:
self.debug.print_debug(
self, 'front or bookpart metadata unspecified')
sys.exit(1)
else:
bg.insert(0, bpm)
else:
self.debug.print_debug(self, 'front metadata unspecified')
else:
self.debug.print_debug(
self, pth + self.gv.PROJECT_INPUT_FILE_DOES_NOT_EXIST)
sys.exit(1)
return self.tr
def create_metadata_path(self, metadata):
"""
creates the correct folder path for the metadata file. Metadata files should be in a folder : metadata
Parameters
----------
metadata : str
Suffix of the metadata files
Returns
-------
pth : str
Correct path of the metadata file in the folder structure
Notes
-----
We assume that metadata files are stored in a sub-folder named metadata
"""
p = os.path.dirname(self.f).split(os.sep)
f = os.path.basename(self.f)
name, ext = os.path.splitext(f)
file_name = [name, '.', metadata, ext]
if not self.stand_alone or not os.path.exists(os.sep.join(p)):
del p[-4:]
p.append('metadata')
p.append(''.join(file_name))
pth = os.sep.join(p)
return pth
def sort_by_tags(self, tag_list, elem):
"""
Sorts a list of elements alphabetically
Parameters
----------
tag_list : list
A list of tag types
elem : Element
Element to be modified
"""
data = []
for e in elem:
vl = []
for tag in tag_list:
vl.append(e.findtext(".//" + tag))
vl.append(e)
data.append(tuple(vl))
data.sort()
elem[:] = [item[-1] for item in data]
def sort_references(self, tag_list):
"""
Sort references based on the sub-elements list
Parameters
----------
tag_list : list
A list of tag types
Returns
-------
tr : elementTree
Element tree of the current file
See Also
--------
sort_by_tags
"""
elem = self.tr.find('./back/ref-list')
self.sort_by_tags(tag_list, elem)
return self.tr
def sort_footnotes(self, tag_list):
"""
Sort footnotes based on the sub-elements list
Parameters
----------
tag_list : list
A list of tag types
Returns
-------
tr : elementTree
Element tree of the current file
See Also
--------
sort_by_tags
"""
elem = self.tr.find('./back/fn-group')
self.sort_by_tags(tag_list, elem)
return self.tr
def process(self):
"""
Process JATS-XML file and do all transformations into the elementtree
See Also
--------
merge_metadata, set_numbering_tags,set_uuids_for_back_matter,sort_footnotes,sort_references,set_numbering_values
"""
citations_to_references = self.args.get('--citations-to-references')
clean_references = self.args.get('--clean-references')
set_numbering_tags = self.args.get('--set-numbering-tags')
set_unique_ids = self.args.get('--set-uuids')
sort_footnotes = self.args.get('--sort-footnotes')
sort_references = self.args.get('--sort-references')
set_numbering_values = self.args.get('--set-numbering-values')
metadata = self.args.get('--metadata')
self.tr = self.merge_metadata(metadata) if metadata else self.tr
self.tr = self.citations_to_references(
) if citations_to_references else self.tr
self.tr = self.clean_references() if clean_references else self.tr
self.tr = self.gv.set_numbering_tags(
set_numbering_tags.split(','),
self.tr) if set_numbering_tags else self.tr
self.tr = self.set_uuids_for_back_matter(
set_unique_ids.split(',')) if set_unique_ids else self.tr
self.tr = self.sort_footnotes(
sort_footnotes.split(',')) if sort_footnotes else self.tr
self.tr = self.sort_references(
sort_references.split(',')) if sort_references else self.tr
for s in set_numbering_values.split(';'):
vals = s.split(',')
count = 1
range_count = [0, 0]
if len(vals) > 3:
r = vals[3].lstrip('{').rstrip('}').split(':')
range_count = [int(r[0]), int(r[1])]
self.tr, count = self.set_numbering_values(vals[0], vals[1],
vals[2], count,
range_count)
self.gv.create_dirs_recursive(self.dr.split('/'))
self.create_xml_file(os.path.join(self.dr, os.path.basename(self.f)))
def get_module_name(self):
"""
Reads the name of the module for debugging and logging
Returns
-------
name string
Name of the Module
"""
name = 'prepare'
return name
def create_xml_file(self, pth):
"""
Write the current elementTree into the file path
Parameters
----------
pth : str
Correct path of the metadata file in the folder structure
Raises
------
IOError
I/O operation fails
Notes
-----
Default configuration writes a normalized XML file with XML scheme
"""
try:
self.tr.write(pth, pretty_print=False, xml_declaration=True)
print()
except IOError as e:
print(e)
self.debug.print_debug(self, self.XML_FILE_NOT_CREATED)
def run(self):
"""
Runs the configuration on the processing object
See Also
--------
process
"""
self.process()
class Merge(Debuggable):
"""
Standalone Processing object which merges current JATS/BITS XML file in to the Body of a BITS-XML document.
"""
def __init__(self):
self.args = self.read_command_line()
self.debug = Debug()
self.gv = GV()
self.uid = self.gv.uuid
self.dr = self.args.get("<path>")
self.f = self.args.get("<input_file>")
self.scheme = self.args.get("<scheme>")
self.set_numbering_tags = self.args.get("--set-numbering-tags")
self.tr = etree.parse(os.path.join(self.dr, self.f))
Debuggable.__init__(self, "Main")
if self.args.get("--debug"):
self.debug.enable_debug()
@staticmethod
def read_command_line():
"""
Reads and generates a docopt dictionary from the command line parameters.
Returns
-------
docopt : dictionary
A dictionary, where keys are names of command-line elements such as and values are theparsed values of those
elements.
"""
return docopt(__doc__, version="xmlMerge 0.0.1")
def create_output_bits(self):
"""
Create bits output file, generates a new file, if no file is found.
Otherwise the current file is appended to the book body as a book-part.
See Also
--------
create_book_part_bits, create_book_bits, do_file_io
"""
fuf = os.path.join(self.dr, self.uid)
pt = os.path.join(self.dr, os.path.basename(self.uid))
trf = None
if os.path.isfile(fuf):
trf = etree.parse(fuf)
bp = trf.find(".//book-body")
book_part = self.create_book_part_bits()
bp.append(book_part)
else:
trf = self.create_book_bits()
trf = self.process(trf)
self.do_file_io(
etree.tostring(trf, pretty_print=True, xml_declaration=True, encoding="UTF-8", standalone="yes"), "w", pt
)
def process(self, tr):
"""
Process BITS-XML file and do all transformations into the elementtree
Parameters
----------
tr : elementtree
element tree as input
Returns
-------
tr : elementtree
transformed element tree
See Also
--------
globals.set_numbering_tags(), set_book_part_attributes()
"""
tr = self.gv.set_numbering_tags(self.set_numbering_tags.split(","), tr) if self.set_numbering_tags else tr
self.set_book_part_attributes(tr)
return tr
def set_book_part_attributes(self, tr):
"""
Add specific attributes to book-part
Parameters
----------
tr : elementtree
element tree as input
Returns
-------
tr : elementtree
transformed element tree
"""
book_parts = tr.findall(".//book-part")
for i, b in enumerate(book_parts):
b.attrib["id"] = "ch_" + str(i)
b.attrib["book-part-type"] = "chapter"
return tr
def create_metadata_path(self, metadata):
"""
creates the correct folder path for the metadata file. Metadata files should be in a folder : metadata
Parameters
----------
metadata : str
Suffix of the metadata files
Returns
-------
pth : str
Correct path of the metadata file in the folder structure
Notes
-----
We assume that metadata files are stored in a sub-folder named metadata
"""
p = os.path.dirname(self.f).split(os.sep)
del p[-4:]
name, ext = os.path.splitext(os.path.basename(self.uid))
file_name = [name, ".", metadata, ext]
p.append("metadata")
p.append("".join(file_name))
pth = os.sep.join(p)
return pth
def create_book_bits(self):
"""
creates a full BITS XML book and optionally adds metadata
Returns
-------
book : elementtree
Elementtree which complies to BITS XML Schheme.
See Also
---------
create_metadata_path, create_book_part_bits
"""
nsmap = {
"xlink": "http://www.w3.org/1999/xlink",
"mml": "http://www.w3.org/1998/Math/MathML",
"xml": "http://www.w3.org/XML/1998/namespace",
}
book = etree.Element(etree.QName("book"), nsmap=nsmap)
book.attrib["dtd-version"] = "2.1"
book.attrib[etree.QName("{http://www.w3.org/XML/1998/namespace}lang")] = "de"
book.attrib["book-type"] = "proceedings"
metadata = self.args.get("--metadata")
if metadata:
pth = self.create_metadata_path(metadata)
if os.path.isfile(pth):
bp = etree.parse(pth).find(".//book-meta")
book.insert(0, bp)
bd = etree.Element("book-body")
bpbd = self.create_book_part_bits()
bd.append(bpbd)
book.append(bd)
return book
def create_book_part_bits(self):
"""
Reads a JATS XMl File and creates a book-part element tree according to BITS-XML.
Returns
-------
bp : elementtree
Book part elementTree
"""
f, bd, bk = self.get_xml_parts()
bp = etree.Element("book-part")
if f is not None:
if len(f):
bp.append(f)
bp.append(bd)
bp.append(bk)
return bp
def get_xml_parts(self):
"""
Returns the front-matter , body and back-matter of a JATS XML file in the above order
Returns
-------
f : elementtree
Front-matter of JATS elementTree
bd : elementtree
Body of JATS elementTree
bk : elementtree
Back-matter of JATS elementTree
"""
r = self.tr.getroot()
f = r.find(".//front")
if f is None:
f = r.find(".//book-part-meta")
bd = r.find(".//body")
bk = r.find(".//back")
return f, bd, bk
def do_file_io(self, s, mode, pth):
"""
Executes read or write operations on a path
Parameters
----------
s: str
Content to be written or None for read
mode: str
w for write , r for r
pth : str
Path to the file to be read or written
Raises
------
IOError
I/O operation fails
"""
try:
w = open(pth, mode)
if mode == "w":
w.write(s)
w.close()
if mode == "r":
o = w.read()
w.close()
except IOError as i:
self.debug.print_debug(self, i)
print(i)
sys.exit(1)
def run(self):
"""
Runs the configuration on the processing object. Process JATS-XML file and merges it into the full BITS-XML file
See Also
--------
create_output_bits
Warning
-------
function create_output_jats not yet used
"""
self.gv.create_dirs_recursive(self.dr.split("/"))
if self.scheme == "bits":
self.create_output_bits()
elif self.scheme == "jats":
self.tr = self.create_output_jats(self.tr)
class Process(Debuggable):
"""
Standalone Processing object to combine, clean and modify a JATS XML file and optionally inject BITS Metadata headers.
Features
--------
add Id numbering for any tag type, clean comments, remove unused references,
set numbering, add unique ids to certain tag types, sort references
"""
def __init__(self):
self.args = self.read_command_line()
self.debug = Debug()
self.gv = GV()
Debuggable.__init__(self, 'Main')
if self.args.get('--debug'):
self.debug.enable_debug()
self.dr = self.args.get('<path>')
self.f = self.args.get('<input_file>')
self.tr = etree.parse(os.path.join(self.dr, self.f))
@staticmethod
def read_command_line():
"""
Reads and generates a docopt dictionary from the command line parameters.
Returns
-------
docopt : dictionary
A dictionary, where keys are names of command-line elements such as and values are theparsed values of those
elements.
"""
return docopt(__doc__, version='xml 0.1')
def remove_references(self):
""" removes references, which are not linked.
Parameters
-----------
tag : str
name of the XML tag
Returns
-------
tr : elementtree
See Also
--------
remove_element, remove_tags
"""
r = self.tr.getroot()
for e in r.findall('.//back/ref-list/ref'):
if e.attrib.get('id'):
if r.find(".//xref[@ref-type='bibr'][@rid='" + e.attrib.get('id') + "']") is None:
self.remove_element(e)
else:
self.remove_element(e)
for e in r.findall(".//xref[@ref-type='bibr']"):
if r.find(".//back/ref-list/ref[@id='" + e.attrib.get('rid') + "']") is None:
if e.getparent() is not None:
for c in e.getparent().getiterator():
if c.tag == 'xref' and c.attrib.get('ref-type') == 'bibr':
self.remove_tags(c)
return self.tr
def remove_tags(self, e):
"""
Takes an etree element and replaces it with its own text
Parameters
----------
e : element
Element to be replaced
"""
if e.getparent() is not None:
previous = e.getprevious()
if previous is not None:
if previous.tail:
if e.text:
previous.tail = previous.tail + e.text
if e.tail:
previous.tail = previous.tail + e.tail
e.getparent().remove(e)
def remove_element(self, e):
"""
Remove any element only if it has a parent
Parameters
----------
e : element
Element to be replaced
"""
if e.getparent() is not None:
e.getparent().remove(e)
def set_uuids_for_back_matter(self, tags):
"""
Add unique id tags to any of the sub-elements of the back matter
Parameters
----------
tags: list
list of elements
Returns
-------
tr : elementtree
"""
for s in tags:
f = {}
ref_type = 'bibr' if s == 'ref' else s
fns = self.tr.getroot().findall(
''.join(['.//xref/[@ref-type="', ref_type, '"]']))
for i in fns:
rid = ''.join(['bibd', uuid.uuid4().get_hex()])
f[i.attrib['rid']] = rid
i.set('rid', rid)
for m in f.keys():
n = self.tr.getroot().find(
''.join(['.//' + s + '/[@id="', m, '"]']))
if n is not None:
n.set('id', f[m]) if len(n) > 0 else ''
return self.tr
def set_numbering_values(
self,
tag,
attr,
value,
count,
range_list):
"""
Adds numerical values to a tag in arguments list
Parameters
---------
tag: str
xml tag name
attr: str
attribute name
value :str
value name
count : int
current sequence number
range_list : list
lower and upper level for the numbering
See Also
--------
set_roman_numbers
"""
searchTag = './/' + tag + '[@' + attr + '="' + value + '"]'
elems = self.tr.getroot().findall(searchTag)
range_count = 1
for elem in elems:
elem.text, range_count = self.set_roman_numbers(
count, range_count, range_list)
count += 1
return self.tr, count
def convert_int_to_roman(self, i):
"""
Converts an integer number into a roman number
Parameters
---------
i : int
integer number
Returns
-------
result : str
Roman number
"""
result = []
for integer, numeral in self.gv.numeral_map:
count = i // integer
result.append(numeral * count)
i -= integer * count
return ''.join(result)
def set_roman_numbers(self, count, r_count, range_list):
"""
Converts a given set of elements defined by range_array into roman numbers
Parameters
---------
count :int
r_count : int
range_list : list
lower and upper level for the numbering
Returns
-------
val : str
r_count: int
See Also
--------
convert_int_to_roman
"""
val = str(count)
if int(range_list[0]) <= count <= int(range_list[1]):
val = self.convert_int_to_roman(r_count).lower()
r_count += 1
else:
val = str(count - r_count + 1)
return val, r_count
def merge_metadata(self, metadata):
"""
reads a metadata file path and merge its content into the metadata section
Parameters
----------
metadata : str
suffix of the metadata files
Returns
-------
tr : elementTree
Element tree of the current file
See Also
-------
create_metadata_path
"""
r = self.tr.getroot()
pth = self.create_metadata_path(metadata)
if os.path.isfile(pth):
fr = r.find('.//front')
fr.getparent().remove(fr)
bpm = etree.parse(pth).find('.//book-part-meta')
bg = r.find('.//body').getparent()
bg.insert(0, bpm)
else:
self.debug.print_debug(self, pth +
self.gv.PROJECT_INPUT_FILE_DOES_NOT_EXIST)
return self.tr
def create_metadata_path(self, metadata):
"""
creates the correct folder path for the metadata file. Metadata files should be in a folder : metadata
Parameters
----------
metadata : str
Suffix of the metadata files
Returns
-------
pth : str
Correct path of the metadata file in the folder structure
Notes
-----
We assume that metadata files are stored in a sub-folder named metadata
"""
p = os.path.dirname(self.f).split(os.sep)
del p[-4:]
f = os.path.basename(self.f)
name, ext = os.path.splitext(f)
file_name = [name, '.', metadata, ext]
p.append('metadata')
p.append(''.join(file_name))
pth = os.sep.join(p)
return pth
def sort_by_tags(self, tag_list, elem):
"""
Sorts a list of elements alphabetically
Parameters
----------
tag_list : list
A list of tag types
elem : Element
Element to be modified
"""
data = []
for e in elem:
vl = []
for tag in tag_list:
vl.append(e.findtext(".//" + tag))
vl.append(e)
data.append(tuple(vl))
data.sort()
elem[:] = [item[-1] for item in data]
def sort_references(self, tag_list):
"""
Sort references based on the sub-elements list
Parameters
----------
tag_list : list
A list of tag types
Returns
-------
tr : elementTree
Element tree of the current file
See Also
--------
sort_by_tags
"""
elem = self.tr.find('./back/ref-list')
self.sort_by_tags(tag_list, elem)
return self.tr
def sort_footnotes(self, tag_list):
"""
Sort footnotes based on the sub-elements list
Parameters
----------
tag_list : list
A list of tag types
Returns
-------
tr : elementTree
Element tree of the current file
See Also
--------
sort_by_tags
"""
elem = self.tr.find('./back/fn-group')
self.sort_by_tags(tag_list, elem)
return self.tr
def process(self):
"""
Process JATS-XML file and do all transformations into the elementtree
See Also
--------
merge_metadata, set_numbering_tags,set_uuids_for_back_matter,sort_footnotes,sort_references,set_numbering_values
"""
clean_references = self.args.get('--clean-references')
set_numbering_tags = self.args.get('--set-numbering-tags')
set_unique_ids = self.args.get('--set-uuids')
sort_footnotes = self.args.get('--sort-footnotes')
sort_references = self.args.get('--sort-references')
set_numbering_values = self.args.get('--set-numbering-values')
metadata = self.args.get('--metadata')
self.tr = self.merge_metadata(metadata) if metadata else self.tr
self.tr = self.remove_references() if clean_references else self.tr
self.tr = self.gv.set_numbering_tags(set_numbering_tags.split(
','), self.tr) if set_numbering_tags else self.tr
self.tr = self.set_uuids_for_back_matter(
set_unique_ids.split(',')) if set_unique_ids else self.tr
self.tr = self.sort_footnotes(
sort_footnotes.split(',')) if sort_footnotes else self.tr
self.tr = self.sort_references(
sort_references.split(',')) if sort_references else self.tr
for s in set_numbering_values.split(';'):
vals = s.split(',')
count = 1
range_count = [0, 0]
if len(vals) > 3:
r = vals[3].lstrip('{').rstrip('}').split(':')
range_count = [int(r[0]), int(r[1])]
self.tr, count = self.set_numbering_values(
vals[0], vals[1], vals[2], count, range_count)
self.gv.create_dirs_recursive(self.dr.split('/'))
self.create_xml_file(
os.path.join(
self.dr, os.path.basename(
self.f)))
def create_xml_file(self, pth):
"""
Write the current elementTree into the file path
Parameters
----------
pth : str
Correct path of the metadata file in the folder structure
Raises
------
IOError
I/O operation fails
Notes
-----
Default configuration writes a normalized XML file with XML scheme
"""
try:
self.tr.write(
pth,
pretty_print=False,
xml_declaration=True
)
print
except IOError as e:
print e
self.debug.print_debug(self, self.XML_FILE_NOT_CREATED)
def run(self):
"""
Runs the configuration on the processing object
See Also
--------
process
"""
self.process()
