-
Notifications
You must be signed in to change notification settings - Fork 6
/
Copy pathcitation.py
232 lines (187 loc) · 8.4 KB
/
citation.py
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
220
221
222
223
224
225
226
227
228
229
230
231
232
import html
from citeproc import formatter, CitationStylesBibliography, Citation, CitationItem
from citeproc.source.json import CiteProcJSON
from enhanced_citation_style import EnhancedCitationStyle, get_style_name
from steps.utils import author_name_as_dict
def display_citation(bibtex_metadata, bib_stylename, formatter=formatter.html):
# valid style names: plos, apa, pnas, nature, bmj, harvard1
# full list is here: https://github.com/citation-style-language/styles
bib_style = EnhancedCitationStyle(bib_stylename)
bibliography = CitationStylesBibliography(
bib_style, bibtex_metadata, formatter
) # could be formatter.html
citation = Citation([CitationItem("ITEM-1")])
bibliography.register(citation)
citation_parts = "".join(bibliography.bibliography()[0])
citation_text = "".join(citation_parts)
if bib_stylename == "apa":
# strip extra periods and spaces that can occur in APA format
citation_text = citation_text.replace("..", ".")
citation_text = citation_text.replace(" ", " ")
citation_text = citation_text.strip()
# strip leading comma
if citation_text.startswith(","):
citation_text = citation_text.lstrip(",").strip()
citation_text = strip_duplicate_apa_title(bibtex_metadata, citation_text)
citation_text = html.unescape(citation_text)
return citation_text
def get_author_list(data_author):
author_list = []
for name_dict in data_author:
new_name_dict = {}
if "family" not in name_dict:
if "name" in name_dict:
new_name_dict["family"] = name_dict["name"]
else:
new_name_dict["family"] = ""
for name_k, name_v in name_dict.items():
if name_k == "literal":
new_name_dict = author_name_as_dict(name_v)
else:
new_name_dict[name_k] = name_v
author_list.append(new_name_dict)
return author_list
def build_bibtex_author_list(authors):
author_list = ""
for i, author in enumerate(authors):
if i > 0:
author_list += " and "
if author.get("family"):
author_list += author.get("family")
if author.get("given"):
author_list += ", " + author.get("given")
return author_list
def bibtex_pages_format(pages):
return pages.replace("-", "--")
def get_bib_source_from_dict(data):
data["id"] = "ITEM-1"
if "author" in data:
data["author"] = get_author_list(data["author"])
if "type" not in data:
data["type"] = "misc"
if data["type"] != "software":
for k, val in data.items():
if val and (k in ["title", "container-title"]):
num_upper = sum([1 for c in val if c.isupper()])
if num_upper > 0.75 * len(val):
data[k] = val.title()
if "page" in data and data["page"] == "-":
del data["page"]
if "bibtex" in data:
del data["bibtex"]
if "issued" in data:
if data["issued"]["date-parts"][0][0] is None:
del data["issued"]
bib_source = CiteProcJSON([data])
return bib_source
def strip_duplicate_apa_title(bibtex_metadata, citation_text):
item = bibtex_metadata.get("item-1")
title = item.get("title")
if title and "Retrieved from https://github.com" not in citation_text:
title = "".join(title).replace(" ", " ")
if citation_text.count(title) == 2:
citation_text = citation_text.replace(title, "", 1)
if citation_text[0] == ".":
citation_text = citation_text.replace(".", "", 1)
citation_text = citation_text.lstrip()
return citation_text
def citations(bibtex_metadata):
response = []
# full list of possible citation formats is here: https://github.com/citation-style-language/styles
for bib_stylename in [
"apa",
"harvard1",
"nature",
"modern-language-association-with-url",
"chicago-author-date",
"vancouver",
]:
citation_style_object = {
"style_shortname": bib_stylename,
"citation": display_citation(bibtex_metadata, bib_stylename),
"style_fullname": get_style_name(bib_stylename),
}
response.append(citation_style_object)
return response
def export_contents(export_type, metadata_dict):
if export_type == "csv":
items = list(metadata_dict.items())
header_row = ",".join([name for (name, value) in items])
try:
value_row = ",".join([str(value) for (name, value) in items])
except UnicodeEncodeError:
value_row = ""
response = "{}\n{}".format(header_row, value_row)
return response
elif export_type == "ris":
response_list = []
response_list.append(("TY", "JOUR"))
response_list.append(("T1", metadata_dict.get("title", "")))
response_list.append(("JO", metadata_dict.get("container-title", "")))
response_list.append(("VL", metadata_dict.get("volume", "")))
response_list.append(("IS", metadata_dict.get("issue", "")))
response_list.append(("SP", metadata_dict.get("page", "")))
response_list.append(("V1", metadata_dict.get("year", "")))
response_list.append(("PB", metadata_dict.get("publisher", "")))
for author in metadata_dict.get("author", []):
response_list.append(
("A1", ", ".join([author.get("family", ""), author.get("given", "")]))
)
response = "\n".join("{} - {}".format(k, v) for (k, v) in response_list)
response += "\nER - "
return response
elif export_type == "enw":
response_list = []
response_list.append(("%T", metadata_dict.get("title", "")))
response_list.append(("%J", metadata_dict.get("container-title", "")))
response_list.append(("%V", metadata_dict.get("volume", "")))
response_list.append(("%N", metadata_dict.get("issue", "")))
response_list.append(("%P", metadata_dict.get("page", "")))
response_list.append(("%D", metadata_dict.get("year", "")))
response_list.append(("%I", metadata_dict.get("publisher", "")))
response_list.append(("0%", "Journal Article"))
for author in metadata_dict.get("author", []):
response_list.append(
("%A", ", ".join([author.get("family", ""), author.get("given", "")]))
)
response = "\n".join("{} {}".format(k, v) for (k, v) in response_list)
return response
elif export_type == "bibtex":
if metadata_dict.get("type"):
response = "@" + metadata_dict.get("type") + "{ITEM1, "
else:
response = "@article{ITEM1, "
response_list = []
response_list.append(("title", metadata_dict.get("title", "")))
# handle book type differently
if metadata_dict.get("type") == "book":
response_list.append(("isbn", metadata_dict.get("isbn", "")))
elif metadata_dict.get("type") == "software":
response_list.append(("url", metadata_dict.get("URL", "")))
response_list.append(("journal", metadata_dict.get("container-title", "")))
response_list.append(("volume", metadata_dict.get("volume", "")))
response_list.append(("number", metadata_dict.get("number", "")))
else:
response_list.append(("journal", metadata_dict.get("container-title", "")))
response_list.append(("volume", metadata_dict.get("volume", "")))
response_list.append(("number", metadata_dict.get("number", "")))
response_list.append(
("pages", bibtex_pages_format(metadata_dict.get("page", "")))
)
response_list.append(("year", metadata_dict.get("year", "")))
response_list.append(("publisher", metadata_dict.get("publisher", "")))
author_list = build_bibtex_author_list(metadata_dict.get("author", []))
response_list.append(("author", author_list))
response += ",\n".join("{}={{{}}}".format(k, v) for (k, v) in response_list)
response += "}"
return response
return None
def reference_manager_exports(metadata_dict):
response = []
for export_name in ["csv", "enw", "ris", "bibtex"]:
export_object = {
"export_name": export_name,
"export": export_contents(export_name, metadata_dict),
}
response.append(export_object)
return response