def get_authors_tags():
"""
Get the tags for main author, coauthors, alternative authors from config
"""
config = load_config_file('citation')
function = config.get("rank_method", "function")
tags_names = [
'first_author',
'additional_author',
'alternative_author_name',
'collaboration_name',
]
tags = {}
for t in tags_names:
r_tag = config.get(function, t)
tags[t] = tagify(parse_tag(r_tag))
return tags
def get_authors_tags():
"""
Get the tags for main author, coauthors, alternative authors from config
"""
config = load_config_file('citation')
function = config.get("rank_method", "function")
tags_names = [
'first_author',
'additional_author',
'alternative_author_name',
'collaboration_name',
]
tags = {}
for t in tags_names:
r_tag = config.get(function, t)
tags[t] = tagify(parse_tag(r_tag))
return tags
def control_field(self, tag, escape=0):
"""
Returns the value of control field given by tag in record
:param tag: the marc code of a field
:param escape: 1 if returned value should be escaped. Else 0.
@return: value of field tag in record
"""
if self.get_record() is None:
#Case where BibRecord could not parse object
return ''
p_tag = parse_tag(tag)
field_value = record_get_field_value(self.get_record(),
p_tag[0],
p_tag[1],
p_tag[2],
p_tag[3])
if escape == 0:
return field_value
else:
return escape_field(field_value, escape)
def fields(self, tag, escape=0, repeatable_subfields_p=False):
"""
Returns the list of values corresonding to "tag".
If tag has an undefined subcode (such as 999C5),
the function returns a list of dictionaries, whoose keys
are the subcodes and the values are the values of tag.subcode.
If the tag has a subcode, simply returns list of values
corresponding to tag.
Eg. for given MARC::
999C5 $a value_1a $b value_1b
999C5 $b value_2b
999C5 $b value_3b $b value_3b_bis
>>> bfo.fields('999C5b')
>>> ['value_1b', 'value_2b', 'value_3b', 'value_3b_bis']
>>> bfo.fields('999C5')
>>> [{'a':'value_1a', 'b':'value_1b'},
{'b':'value_2b'},
{'b':'value_3b'}]
By default the function returns only one value for each
subfield (that is it considers that repeatable subfields are
not allowed). It is why in the above example 'value3b_bis' is
not shown for bfo.fields('999C5'). (Note that it is not
defined which of value_3b or value_3b_bis is returned). This
is to simplify the use of the function, as most of the time
subfields are not repeatable (in that way we get a string
instead of a list). You can allow repeatable subfields by
setting 'repeatable_subfields_p' parameter to True. In
this mode, the above example would return:
>>> bfo.fields('999C5b', repeatable_subfields_p=True)
>>> ['value_1b', 'value_2b', 'value_3b']
>>> bfo.fields('999C5', repeatable_subfields_p=True)
>>> [{'a':['value_1a'], 'b':['value_1b']},
{'b':['value_2b']},
{'b':['value_3b', 'value3b_bis']}]
NOTICE THAT THE RETURNED STRUCTURE IS DIFFERENT. Also note
that whatever the value of 'repeatable_subfields_p' is,
bfo.fields('999C5b') always show all fields, even repeatable
ones. This is because the parameter has no impact on the
returned structure (it is always a list).
'escape' parameter allows to escape special characters
of the fields. The value of escape can be:
0. No escaping
1. Escape all HTML characters
2. Remove unsafe HTML tags (Eg. keep <br />)
3. Mix of mode 1 and 2. If value of field starts with
<!-- HTML -->, then use mode 2. Else use mode 1.
4. Remove all HTML tags
5. Same as 2, with more tags allowed (like <img>)
6. Same as 3, with more tags allowed (like <img>)
7. Mix of mode 0 and mode 1. If field_value
starts with <!--HTML-->, then use mode 0.
Else use mode 1.
8. Same as mode 1, but also escape double-quotes
9. Same as mode 4, but also escape double-quotes
:param tag: the marc code of a field
:param escape: 1 if returned values should be escaped. Else 0.
@repeatable_subfields_p if True, returns the list of subfields in the dictionary
@return: values of field tag in record
"""
if self.get_record() is None:
# Case where BibRecord could not parse object
return []
p_tag = parse_tag(tag)
if p_tag[3] != "":
# Subcode has been defined. Simply returns list of values
values = record_get_field_values(self.get_record(),
p_tag[0],
p_tag[1],
p_tag[2],
p_tag[3])
if escape == 0:
return values
else:
return [escape_field(value, escape) for value in values]
else:
# Subcode is undefined. Returns list of dicts.
# However it might be the case of a control field.
instances = record_get_field_instances(self.get_record(),
p_tag[0],
p_tag[1],
p_tag[2])
if repeatable_subfields_p:
list_of_instances = []
for instance in instances:
instance_dict = {}
for subfield in instance[0]:
if subfield[0] not in instance_dict:
instance_dict[subfield[0]] = []
if escape == 0:
instance_dict[subfield[0]].append(subfield[1])
else:
instance_dict[subfield[0]].append(escape_field(subfield[1], escape))
list_of_instances.append(instance_dict)
return list_of_instances
else:
if escape == 0:
return [dict(instance[0]) for instance in instances]
else:
return [dict([(subfield[0], escape_field(subfield[1], escape))
for subfield in instance[0]])
for instance in instances]
def get_tags_config(config):
"""Fetch needs config from our config file"""
# Probably "citation" unless this file gets renamed
function = config.get("rank_method", "function")
write_message("config function %s" % function, verbose=9)
tags = {}
# 037a: contains (often) the "hep-ph/0501084" tag of THIS record
try:
tag = config.get(function, "primary_report_number")
except ConfigParser.NoOptionError:
tags['record_pri_number'] = None
else:
tags['record_pri_number'] = tagify(parse_tag(tag))
# 088a: additional short identifier for the record
try:
tag = config.get(function, "additional_report_number")
except ConfigParser.NoOptionError:
tags['record_add_number'] = None
else:
tags['record_add_number'] = tagify(parse_tag(tag))
# 999C5r. this is in the reference list, refers to other records.
# Looks like: hep-ph/0408002
try:
tag = config.get(function, "reference_via_report_number")
except ConfigParser.NoOptionError:
tags['refs_report_number'] = None
else:
tags['refs_report_number'] = tagify(parse_tag(tag))
# 999C5s. this is in the reference list, refers to other records.
# Looks like: Phys.Rev.,A21,78
try:
tag = config.get(function, "reference_via_pubinfo")
except ConfigParser.NoOptionError:
tags['refs_journal'] = None
else:
tags['refs_journal'] = tagify(parse_tag(tag))
# 999C5a. this is in the reference list, refers to other records.
# Looks like: 10.1007/BF03170733
try:
tag = config.get(function, "reference_via_doi")
except ConfigParser.NoOptionError:
tags['refs_doi'] = None
else:
tags['refs_doi'] = tagify(parse_tag(tag))
# 999C50. this is in the reference list, refers to other records.
# Looks like: 1205
try:
tag = config.get(function, "reference_via_record_id")
except ConfigParser.NoOptionError:
tags['refs_record_id'] = None
else:
tags['refs_record_id'] = tagify(parse_tag(tag))
# 999C5i. this is in the reference list, refers to other records.
# Looks like: 9781439520031
try:
tag = config.get(function, "reference_via_isbn")
except ConfigParser.NoOptionError:
tags['refs_isbn'] = None
else:
tags['refs_isbn'] = tagify(parse_tag(tag))
# Fields needed to construct the journals for this record
try:
tag = {
'pages': config.get(function, "pubinfo_journal_page"),
'year': config.get(function, "pubinfo_journal_year"),
'journal': config.get(function, "pubinfo_journal_title"),
'volume': config.get(function, "pubinfo_journal_volume"),
}
except ConfigParser.NoOptionError:
tags['publication'] = None
else:
tags['publication'] = {
'pages': tagify(parse_tag(tag['pages'])),
'year': tagify(parse_tag(tag['year'])),
'journal': tagify(parse_tag(tag['journal'])),
'volume': tagify(parse_tag(tag['volume'])),
}
# Fields needed to lookup the DOIs
tags['doi'] = get_field_tags('doi')
# Fields needed to lookup the ISBN
tags['isbn'] = get_field_tags('isbn')
# 999C5s. A standardized way of writing a reference in the reference list.
# Like: Nucl. Phys. B 710 (2000) 371
try:
tags['publication_format'] = config.get(function,
"pubinfo_journal_format")
except ConfigParser.NoOptionError:
tags['publication_format'] = CFG_JOURNAL_PUBINFO_STANDARD_FORM
# Print values of tags for debugging
write_message("tag values: %r" % [tags], verbose=9)
return tags
def get_tags_config(config):
"""Fetch needs config from our config file"""
# Probably "citation" unless this file gets renamed
function = config.get("rank_method", "function")
write_message("config function %s" % function, verbose=9)
tags = {}
# 037a: contains (often) the "hep-ph/0501084" tag of THIS record
try:
tag = config.get(function, "primary_report_number")
except ConfigParser.NoOptionError:
tags["record_pri_number"] = None
else:
tags["record_pri_number"] = tagify(parse_tag(tag))
# 088a: additional short identifier for the record
try:
tag = config.get(function, "additional_report_number")
except ConfigParser.NoOptionError:
tags["record_add_number"] = None
else:
tags["record_add_number"] = tagify(parse_tag(tag))
# 999C5r. this is in the reference list, refers to other records.
# Looks like: hep-ph/0408002
try:
tag = config.get(function, "reference_via_report_number")
except ConfigParser.NoOptionError:
tags["refs_report_number"] = None
else:
tags["refs_report_number"] = tagify(parse_tag(tag))
# 999C5s. this is in the reference list, refers to other records.
# Looks like: Phys.Rev.,A21,78
try:
tag = config.get(function, "reference_via_pubinfo")
except ConfigParser.NoOptionError:
tags["refs_journal"] = None
else:
tags["refs_journal"] = tagify(parse_tag(tag))
# 999C5a. this is in the reference list, refers to other records.
# Looks like: 10.1007/BF03170733
try:
tag = config.get(function, "reference_via_doi")
except ConfigParser.NoOptionError:
tags["refs_doi"] = None
else:
tags["refs_doi"] = tagify(parse_tag(tag))
# 999C50. this is in the reference list, refers to other records.
# Looks like: 1205
try:
tag = config.get(function, "reference_via_record_id")
except ConfigParser.NoOptionError:
tags["refs_record_id"] = None
else:
tags["refs_record_id"] = tagify(parse_tag(tag))
# 999C5i. this is in the reference list, refers to other records.
# Looks like: 9781439520031
try:
tag = config.get(function, "reference_via_isbn")
except ConfigParser.NoOptionError:
tags["refs_isbn"] = None
else:
tags["refs_isbn"] = tagify(parse_tag(tag))
# Fields needed to construct the journals for this record
try:
tag = {
"pages": config.get(function, "pubinfo_journal_page"),
"year": config.get(function, "pubinfo_journal_year"),
"journal": config.get(function, "pubinfo_journal_title"),
"volume": config.get(function, "pubinfo_journal_volume"),
}
except ConfigParser.NoOptionError:
tags["publication"] = None
else:
tags["publication"] = {
"pages": tagify(parse_tag(tag["pages"])),
"year": tagify(parse_tag(tag["year"])),
"journal": tagify(parse_tag(tag["journal"])),
"volume": tagify(parse_tag(tag["volume"])),
}
# Fields needed to lookup the DOIs
tags["doi"] = get_field_tags("doi")
# Fields needed to lookup the ISBN
tags["isbn"] = get_field_tags("isbn")
# 999C5s. A standardized way of writing a reference in the reference list.
# Like: Nucl. Phys. B 710 (2000) 371
try:
tags["publication_format"] = config.get(function, "pubinfo_journal_format")
except ConfigParser.NoOptionError:
tags["publication_format"] = CFG_JOURNAL_PUBINFO_STANDARD_FORM
# Print values of tags for debugging
write_message("tag values: %r" % [tags], verbose=9)
return tags
def format_element(bfo, tag, limit, instances_separator=" ",
subfields_separator=" ", extension="", output_pattern=""):
"""
Prints the given field of a record.
If tag is in range [001, 010], this element assumes
that it accesses a control field. Else it considers it
accesses a data field.
<p>For eg. consider the following metdata:
<pre>
100__ $$aCalatroni, S$$uCERN
245__ $$aStatus of the EP Simulations and Facilities for the SPL
700__ $$aFerreira, L$$uCERN
700__ $$aMacatrao, M$$uCERN
700__ $$aSkala, A$$uCERN
700__ $$aSosin, M$$uCERN
700__ $$ade Waele, R$$uCERN
700__ $$aWithofs, Y$$uKHLim, Diepenbeek
</pre>
The following calls to bfe_field would print:
<pre>
<BFE_FIELD tag="700" instances_separator="<br/>" subfields_separator=" - ">
Ferreira, L - CERN
Macatrao, M - CERN
Skala, A - CERN
Sosin, M - CERN
de Waele, R - CERN
Withofs, Y - KHLim, Diepenbeek
</pre>
</p>
<p>For more advanced formatting, the <code>output_pattern</code>
parameter can be used to output the subfields of each instance in
the specified way. For eg. consider the following metadata:
<pre>
775__ $$b15. Aufl.$$c1995-1996$$nv.1$$pGrundlagen und Werkstoffe$$w317999
775__ $$b12. Aufl.$$c1963$$w278898
775__ $$b14. Aufl.$$c1983$$w107899
775__ $$b13. Aufl.$$c1974$$w99635
</pre>
with the following <code>output_pattern</code>:
<pre>
<a href="/record/%(w)s">%(b)s (%(c)s) %(n)s %(p)s</a>
</pre>
would print:<br/>
<a href="/record/317999">15. Aufl. (1995-1996) v.1 Grundlagen und Werkstoffe</a><br/>
<a href="/record/278898">12. Aufl. (1963) </a><br/>
<a href="/record/107899">14. Aufl. (1983) </a><br/>
<a href="/record/99635">13. Aufl. (1974) </a>
<br/>(<code>instances_separator="<br/>"</code> set for
readability)<br/> The output pattern must follow <a
href="http://docs.python.org/library/stdtypes.html#string-formatting-operations">Python
string formatting</a> syntax. The format must use parenthesized
notation to map to the subfield code. This currently restricts the
support of <code>output_pattern</code> to non-repeatable
subfields</p>
@param tag: the tag code of the field that is to be printed
@param instances_separator: a separator between instances of field
@param subfields_separator: a separator between subfields of an instance
@param limit: the maximum number of values to display.
@param extension: a text printed at the end if 'limit' has been exceeded
@param output_pattern: when specified, prints the subfields of each instance according to pattern specified as parameter (following Python string formatting convention)
"""
# Check if data or control field
p_tag = parse_tag(tag)
if p_tag[0].isdigit() and int(p_tag[0]) in range(0, 11):
return bfo.control_field(tag)
elif p_tag[0].isdigit():
# Get values without subcode.
# We will filter unneeded subcode later
if p_tag[1] == '':
p_tag[1] = '_'
if p_tag[2] == '':
p_tag[2] = '_'
values = bfo.fields(p_tag[0]+p_tag[1]+p_tag[2]) # Values will
# always be a
# list of
# dicts
else:
return ''
x = 0
instances_out = [] # Retain each instance output
for instance in values:
filtered_values = [value for (subcode, value) in iteritems(instance)
if p_tag[3] == '' or p_tag[3] == '%' \
or p_tag[3] == subcode]
if len(filtered_values) > 0:
# We have found some corresponding subcode(s)
if limit.isdigit() and x + len(filtered_values) >= int(limit):
# We are going to exceed the limit
filtered_values = filtered_values[:int(limit)-x] # Takes only needed one
if len(filtered_values) > 0: # do not append empty list!
if output_pattern:
try:
instances_out.append(output_pattern % DictNoKeyError(instance))
except:
pass
else:
instances_out.append(subfields_separator.join(filtered_values))
x += len(filtered_values) # record that so we know limit has been exceeded
break # No need to go further
else:
if output_pattern:
try:
instances_out.append(output_pattern % DictNoKeyError(instance))
except:
pass
else:
instances_out.append(subfields_separator.join(filtered_values))
x += len(filtered_values)
ext_out = ''
if limit.isdigit() and x > int(limit):
ext_out = extension
return instances_separator.join(instances_out) + ext_out
def format_element(bfo, tag, limit, instances_separator=" ",
subfields_separator=" ", extension="", output_pattern=""):
"""
Prints the given field of a record.
If tag is in range [001, 010], this element assumes
that it accesses a control field. Else it considers it
accesses a data field.
<p>For eg. consider the following metdata:
<pre>
100__ $$aCalatroni, S$$uCERN
245__ $$aStatus of the EP Simulations and Facilities for the SPL
700__ $$aFerreira, L$$uCERN
700__ $$aMacatrao, M$$uCERN
700__ $$aSkala, A$$uCERN
700__ $$aSosin, M$$uCERN
700__ $$ade Waele, R$$uCERN
700__ $$aWithofs, Y$$uKHLim, Diepenbeek
</pre>
The following calls to bfe_field would print:
<pre>
<BFE_FIELD tag="700" instances_separator="<br/>" subfields_separator=" - ">
Ferreira, L - CERN
Macatrao, M - CERN
Skala, A - CERN
Sosin, M - CERN
de Waele, R - CERN
Withofs, Y - KHLim, Diepenbeek
</pre>
</p>
<p>For more advanced formatting, the <code>output_pattern</code>
parameter can be used to output the subfields of each instance in
the specified way. For eg. consider the following metadata:
<pre>
775__ $$b15. Aufl.$$c1995-1996$$nv.1$$pGrundlagen und Werkstoffe$$w317999
775__ $$b12. Aufl.$$c1963$$w278898
775__ $$b14. Aufl.$$c1983$$w107899
775__ $$b13. Aufl.$$c1974$$w99635
</pre>
with the following <code>output_pattern</code>:
<pre>
<a href="/record/%(w)s">%(b)s (%(c)s) %(n)s %(p)s</a>
</pre>
would print:<br/>
<a href="/record/317999">15. Aufl. (1995-1996) v.1 Grundlagen und Werkstoffe</a><br/>
<a href="/record/278898">12. Aufl. (1963) </a><br/>
<a href="/record/107899">14. Aufl. (1983) </a><br/>
<a href="/record/99635">13. Aufl. (1974) </a>
<br/>(<code>instances_separator="<br/>"</code> set for
readability)<br/> The output pattern must follow <a
href="http://docs.python.org/library/stdtypes.html#string-formatting-operations">Python
string formatting</a> syntax. The format must use parenthesized
notation to map to the subfield code. This currently restricts the
support of <code>output_pattern</code> to non-repeatable
subfields</p>
@param tag: the tag code of the field that is to be printed
@param instances_separator: a separator between instances of field
@param subfields_separator: a separator between subfields of an instance
@param limit: the maximum number of values to display.
@param extension: a text printed at the end if 'limit' has been exceeded
@param output_pattern: when specified, prints the subfields of each instance according to pattern specified as parameter (following Python string formatting convention)
"""
# Check if data or control field
p_tag = parse_tag(tag)
if p_tag[0].isdigit() and int(p_tag[0]) in range(0, 11):
return bfo.control_field(tag)
elif p_tag[0].isdigit():
# Get values without subcode.
# We will filter unneeded subcode later
if p_tag[1] == '':
p_tag[1] = '_'
if p_tag[2] == '':
p_tag[2] = '_'
values = bfo.fields(p_tag[0]+p_tag[1]+p_tag[2]) # Values will
# always be a
# list of
# dicts
else:
return ''
x = 0
instances_out = [] # Retain each instance output
for instance in values:
filtered_values = [value for (subcode, value) in iteritems(instance)
if p_tag[3] == '' or p_tag[3] == '%' \
or p_tag[3] == subcode]
if len(filtered_values) > 0:
# We have found some corresponding subcode(s)
if limit.isdigit() and x + len(filtered_values) >= int(limit):
# We are going to exceed the limit
filtered_values = filtered_values[:int(limit)-x] # Takes only needed one
if len(filtered_values) > 0: # do not append empty list!
if output_pattern:
try:
instances_out.append(output_pattern % DictNoKeyError(instance))
except:
pass
else:
instances_out.append(subfields_separator.join(filtered_values))
x += len(filtered_values) # record that so we know limit has been exceeded
break # No need to go further
else:
if output_pattern:
try:
instances_out.append(output_pattern % DictNoKeyError(instance))
except:
pass
else:
instances_out.append(subfields_separator.join(filtered_values))
x += len(filtered_values)
ext_out = ''
if limit.isdigit() and x > int(limit):
ext_out = extension
return instances_separator.join(instances_out) + ext_out
