litloop 1.18.3__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- litloop/__init__.py +89 -0
- litloop/__main__.py +6 -0
- litloop/_source_hygiene.py +158 -0
- litloop/agents/__init__.py +13 -0
- litloop/agents/client.py +164 -0
- litloop/agents/runner.py +123 -0
- litloop/agents/system.py +54 -0
- litloop/agents/tools.py +142 -0
- litloop/app_server.py +8 -0
- litloop/browser/__init__.py +1 -0
- litloop/browser/backend.py +1009 -0
- litloop/browser/camofox_api.py +368 -0
- litloop/browser/chrome_copy.py +136 -0
- litloop/browser/cloakbrowser_compat.py +72 -0
- litloop/browser/cookies.py +347 -0
- litloop/browser/engine.py +965 -0
- litloop/browser/login.py +636 -0
- litloop/browser/pdf.py +263 -0
- litloop/browser/profile_health.py +167 -0
- litloop/browser/runtime.py +210 -0
- litloop/cache.py +104 -0
- litloop/citations/__init__.py +1 -0
- litloop/citations/bib_import.py +102 -0
- litloop/citations/bibtex_crossref.py +143 -0
- litloop/citations/formats.py +225 -0
- litloop/citations/paper_list.py +200 -0
- litloop/citations/session_export.py +94 -0
- litloop/cli/__init__.py +12 -0
- litloop/cli/_utils.py +267 -0
- litloop/cli/commands.py +1098 -0
- litloop/cli/doctor.py +141 -0
- litloop/cli/main.py +1173 -0
- litloop/cli/web.py +190 -0
- litloop/config.py +413 -0
- litloop/data/VARCON-LICENSE.txt +62 -0
- litloop/data/elements.tsv +119 -0
- litloop/data/institutional_identity_policy.json +165 -0
- litloop/data/publisher_access_catalog.json +969 -0
- litloop/data/publisher_carsi.json +105 -0
- litloop/data/spelling_search.tsv.gz +0 -0
- litloop/data/spelling_us.tsv.gz +0 -0
- litloop/data/webvpn.dat +0 -0
- litloop/data/webvpn.json +603 -0
- litloop/db.py +1922 -0
- litloop/deps.py +128 -0
- litloop/desktop/__init__.py +1 -0
- litloop/desktop/agent_runner.py +537 -0
- litloop/desktop/download_jobs.py +571 -0
- litloop/desktop/error_text.py +192 -0
- litloop/desktop/server.py +999 -0
- litloop/desktop/settings.py +552 -0
- litloop/desktop/translate.py +103 -0
- litloop/diagnostics.py +126 -0
- litloop/download/__init__.py +1 -0
- litloop/download/doi_check.py +44 -0
- litloop/download/fetcher.py +975 -0
- litloop/download/markdown.py +130 -0
- litloop/download/pdf.py +454 -0
- litloop/download/pipeline.py +1166 -0
- litloop/download/progress.py +312 -0
- litloop/download/rename.py +211 -0
- litloop/extractors/__init__.py +0 -0
- litloop/extractors/html_extractor.py +31 -0
- litloop/extractors/pdf_extractor.py +151 -0
- litloop/extractors/publisher_adapters/__init__.py +0 -0
- litloop/extractors/publisher_adapters/acs.py +167 -0
- litloop/extractors/publisher_adapters/elsevier.py +178 -0
- litloop/extractors/publisher_adapters/generic.py +191 -0
- litloop/extractors/publisher_adapters/nature.py +204 -0
- litloop/extractors/publisher_adapters/rsc.py +154 -0
- litloop/extractors/publisher_adapters/tandfonline.py +154 -0
- litloop/extractors/publisher_adapters/wiley.py +160 -0
- litloop/http_utils.py +57 -0
- litloop/identifiers.py +134 -0
- litloop/institutional/__init__.py +1 -0
- litloop/institutional/auth.py +576 -0
- litloop/institutional/carsi_login.py +569 -0
- litloop/institutional/config_adapter.py +63 -0
- litloop/institutional/proxy_check.py +98 -0
- litloop/institutional/remote_assist.py +274 -0
- litloop/institutional/schools.py +102 -0
- litloop/institutional/session_heal.py +73 -0
- litloop/institutional/session_store.py +105 -0
- litloop/log.py +47 -0
- litloop/models.py +269 -0
- litloop/network.py +417 -0
- litloop/optional.py +310 -0
- litloop/publishers/__init__.py +1 -0
- litloop/publishers/access.py +232 -0
- litloop/publishers/pdf_router.py +451 -0
- litloop/publishers/profiles.py +899 -0
- litloop/publishers/strategies/__init__.py +122 -0
- litloop/publishers/strategies/_core.py +2340 -0
- litloop/publishers/strategies/_elsevier_api.py +578 -0
- litloop/publishers/strategies/acm.py +27 -0
- litloop/publishers/strategies/acs.py +42 -0
- litloop/publishers/strategies/aip.py +27 -0
- litloop/publishers/strategies/aps.py +29 -0
- litloop/publishers/strategies/asce.py +28 -0
- litloop/publishers/strategies/base.py +108 -0
- litloop/publishers/strategies/copernicus.py +24 -0
- litloop/publishers/strategies/elsevier.py +66 -0
- litloop/publishers/strategies/generic.py +39 -0
- litloop/publishers/strategies/ieee.py +28 -0
- litloop/publishers/strategies/iop.py +27 -0
- litloop/publishers/strategies/nature.py +27 -0
- litloop/publishers/strategies/oxford.py +27 -0
- litloop/publishers/strategies/registry.py +83 -0
- litloop/publishers/strategies/royalsociety.py +28 -0
- litloop/publishers/strategies/rsc.py +27 -0
- litloop/publishers/strategies/sage.py +30 -0
- litloop/publishers/strategies/science.py +27 -0
- litloop/publishers/strategies/springer.py +34 -0
- litloop/publishers/strategies/tandfonline.py +32 -0
- litloop/publishers/strategies/wiley.py +32 -0
- litloop/publishers/supplementary.py +219 -0
- litloop/quota.py +202 -0
- litloop/search/__init__.py +1 -0
- litloop/search/abstracts.py +291 -0
- litloop/search/deep.py +1216 -0
- litloop/search/quick.py +1102 -0
- litloop/search/scansci_find.py +410 -0
- litloop/search/screening.py +225 -0
- litloop/search/title_to_doi.py +163 -0
- litloop/search/watches.py +124 -0
- litloop/server.py +1731 -0
- litloop/sources/__init__.py +1339 -0
- litloop/sources/_batch.py +529 -0
- litloop/sources/_index.py +221 -0
- litloop/sources/_routes.py +290 -0
- litloop/sources/altcha.py +90 -0
- litloop/sources/arxiv.py +45 -0
- litloop/sources/attempt.py +91 -0
- litloop/sources/carsi.py +74 -0
- litloop/sources/core_api.py +46 -0
- litloop/sources/crossref.py +162 -0
- litloop/sources/elsevier_api.py +620 -0
- litloop/sources/elsevier_check.py +274 -0
- litloop/sources/europepmc.py +81 -0
- litloop/sources/ezproxy.py +317 -0
- litloop/sources/instsci.py +1295 -0
- litloop/sources/libgen.py +116 -0
- litloop/sources/nature.py +39 -0
- litloop/sources/oa_discovery.py +135 -0
- litloop/sources/openaire.py +122 -0
- litloop/sources/openalex.py +100 -0
- litloop/sources/publishers.py +684 -0
- litloop/sources/sage_cn.py +139 -0
- litloop/sources/scibban.py +10 -0
- litloop/sources/scihub.py +1379 -0
- litloop/sources/scihub_domains.py +203 -0
- litloop/sources/scihub_speed.py +187 -0
- litloop/sources/scoring.py +250 -0
- litloop/sources/semantic_scholar.py +146 -0
- litloop/sources/springer_tdm.py +172 -0
- litloop/sources/unpaywall.py +116 -0
- litloop/sources/vpnsci.py +38 -0
- litloop/store.py +264 -0
- litloop/templates/index.html +347 -0
- litloop/terms/__init__.py +1 -0
- litloop/terms/glossary.py +422 -0
- litloop/terms/spelling.py +89 -0
- litloop/terms/text.py +106 -0
- litloop/tor/__init__.py +1 -0
- litloop/tor/embedded.py +371 -0
- litloop/tor/proxy.py +110 -0
- litloop/updates.py +148 -0
- litloop/zotero/__init__.py +1 -0
- litloop/zotero/bridge.py +309 -0
- litloop/zotero/client.py +317 -0
- litloop-1.18.3.dist-info/METADATA +347 -0
- litloop-1.18.3.dist-info/RECORD +176 -0
- litloop-1.18.3.dist-info/WHEEL +5 -0
- litloop-1.18.3.dist-info/entry_points.txt +2 -0
- litloop-1.18.3.dist-info/licenses/LICENSE +197 -0
- litloop-1.18.3.dist-info/top_level.txt +1 -0
litloop/cache.py
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
1
|
+
"""Cache management for LitLoop."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
import hashlib
|
|
6
|
+
import json
|
|
7
|
+
import time
|
|
8
|
+
from pathlib import Path
|
|
9
|
+
from typing import Any
|
|
10
|
+
|
|
11
|
+
|
|
12
|
+
def cache_key(identifier: str) -> str:
|
|
13
|
+
return hashlib.sha256(identifier.lower().encode("utf-8")).hexdigest()[:24]
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
def cache_path(identifier: str, config: dict[str, Any]) -> Path:
|
|
17
|
+
return Path(config["cache_dir"]) / f"{cache_key(identifier)}.json"
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
def cache_get(identifier: str, config: dict[str, Any]) -> dict[str, Any] | None:
|
|
21
|
+
path = cache_path(identifier, config)
|
|
22
|
+
if not path.exists():
|
|
23
|
+
return None
|
|
24
|
+
ttl = float(config.get("cache_ttl_hours", 168)) * 3600
|
|
25
|
+
if ttl > 0 and time.time() - path.stat().st_mtime > ttl:
|
|
26
|
+
return None
|
|
27
|
+
try:
|
|
28
|
+
with path.open("r", encoding="utf-8") as fh:
|
|
29
|
+
return json.load(fh)
|
|
30
|
+
except Exception:
|
|
31
|
+
return None
|
|
32
|
+
|
|
33
|
+
|
|
34
|
+
def cache_set(identifier: str, result: dict[str, Any], config: dict[str, Any]) -> None:
|
|
35
|
+
cache_dir = Path(config["cache_dir"])
|
|
36
|
+
cache_dir.mkdir(parents=True, exist_ok=True)
|
|
37
|
+
target = cache_path(identifier, config)
|
|
38
|
+
tmp = target.with_suffix(".tmp")
|
|
39
|
+
try:
|
|
40
|
+
with tmp.open("w", encoding="utf-8") as fh:
|
|
41
|
+
json.dump(result, fh, indent=2, ensure_ascii=False)
|
|
42
|
+
tmp.replace(target)
|
|
43
|
+
except Exception:
|
|
44
|
+
tmp.unlink(missing_ok=True)
|
|
45
|
+
raise
|
|
46
|
+
|
|
47
|
+
|
|
48
|
+
def cache_clear(identifier: str | None, config: dict[str, Any]) -> int:
|
|
49
|
+
cache_dir = Path(config["cache_dir"])
|
|
50
|
+
if not cache_dir.exists():
|
|
51
|
+
return 0
|
|
52
|
+
if identifier:
|
|
53
|
+
path = cache_path(identifier, config)
|
|
54
|
+
if path.exists():
|
|
55
|
+
path.unlink()
|
|
56
|
+
return 1
|
|
57
|
+
return 0
|
|
58
|
+
count = 0
|
|
59
|
+
for f in cache_dir.glob("*.json"):
|
|
60
|
+
f.unlink()
|
|
61
|
+
count += 1
|
|
62
|
+
return count
|
|
63
|
+
|
|
64
|
+
|
|
65
|
+
def search_cache_key(payload: dict[str, Any]) -> str:
|
|
66
|
+
raw = json.dumps(payload, sort_keys=True, ensure_ascii=False, default=str)
|
|
67
|
+
return hashlib.sha256(raw.encode("utf-8")).hexdigest()[:24]
|
|
68
|
+
|
|
69
|
+
|
|
70
|
+
def search_cache_path(payload: dict[str, Any], config: dict[str, Any]) -> Path:
|
|
71
|
+
return Path(config["cache_dir"]) / f"search_{search_cache_key(payload)}.json"
|
|
72
|
+
|
|
73
|
+
|
|
74
|
+
def search_cache_get(payload: dict[str, Any], config: dict[str, Any]) -> dict[str, Any] | None:
|
|
75
|
+
ttl_hours = float(config.get("search_cache_ttl_hours", 168))
|
|
76
|
+
if ttl_hours <= 0:
|
|
77
|
+
return None
|
|
78
|
+
path = search_cache_path(payload, config)
|
|
79
|
+
if not path.exists():
|
|
80
|
+
return None
|
|
81
|
+
if time.time() - path.stat().st_mtime > ttl_hours * 3600:
|
|
82
|
+
return None
|
|
83
|
+
try:
|
|
84
|
+
with path.open("r", encoding="utf-8") as fh:
|
|
85
|
+
data = json.load(fh)
|
|
86
|
+
return data if isinstance(data, dict) else None
|
|
87
|
+
except Exception:
|
|
88
|
+
return None
|
|
89
|
+
|
|
90
|
+
|
|
91
|
+
def search_cache_set(payload: dict[str, Any], data: dict[str, Any], config: dict[str, Any]) -> None:
|
|
92
|
+
if float(config.get("search_cache_ttl_hours", 168)) <= 0:
|
|
93
|
+
return
|
|
94
|
+
cache_dir = Path(config["cache_dir"])
|
|
95
|
+
cache_dir.mkdir(parents=True, exist_ok=True)
|
|
96
|
+
target = search_cache_path(payload, config)
|
|
97
|
+
tmp = target.with_name(f".{target.name}.{hash(target) & 0xFFFF:x}.tmp")
|
|
98
|
+
try:
|
|
99
|
+
with tmp.open("w", encoding="utf-8", newline="\n") as fh:
|
|
100
|
+
json.dump(data, fh, indent=2, ensure_ascii=False)
|
|
101
|
+
tmp.replace(target)
|
|
102
|
+
except Exception:
|
|
103
|
+
tmp.unlink(missing_ok=True)
|
|
104
|
+
raise
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
"""Citation formats, BibTeX parsing, paper lists, and session export."""
|
|
@@ -0,0 +1,102 @@
|
|
|
1
|
+
"""BibTeX file parser for bulk import."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
import re
|
|
6
|
+
from pathlib import Path
|
|
7
|
+
from typing import Any
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
def parse_bib_file(file_path: str | Path) -> list[dict[str, str]]:
|
|
11
|
+
"""Parse a .bib file and extract entries with DOIs.
|
|
12
|
+
|
|
13
|
+
Returns list of dicts with keys: cite_key, doi, title, authors, year
|
|
14
|
+
"""
|
|
15
|
+
path = Path(file_path)
|
|
16
|
+
if not path.exists():
|
|
17
|
+
return []
|
|
18
|
+
|
|
19
|
+
try:
|
|
20
|
+
content = path.read_text(encoding="utf-8")
|
|
21
|
+
except UnicodeDecodeError:
|
|
22
|
+
content = path.read_text(encoding="latin-1")
|
|
23
|
+
|
|
24
|
+
return parse_bib_text(content)
|
|
25
|
+
|
|
26
|
+
|
|
27
|
+
def parse_bib_text(content: str, *, require_doi: bool = True) -> list[dict[str, str]]:
|
|
28
|
+
"""Parse BibTeX text and extract entries.
|
|
29
|
+
|
|
30
|
+
Args:
|
|
31
|
+
content: BibTeX text content
|
|
32
|
+
require_doi: If True (default), only return entries with DOI.
|
|
33
|
+
If False, return all entries.
|
|
34
|
+
"""
|
|
35
|
+
entries = []
|
|
36
|
+
# Find entry starts: @type{key,
|
|
37
|
+
entry_start = re.compile(r"@(\w+)\s*\{([^,]+),", re.IGNORECASE)
|
|
38
|
+
|
|
39
|
+
pos = 0
|
|
40
|
+
while pos < len(content):
|
|
41
|
+
m = entry_start.search(content, pos)
|
|
42
|
+
if not m:
|
|
43
|
+
break
|
|
44
|
+
|
|
45
|
+
entry_type = m.group(1).lower()
|
|
46
|
+
cite_key = m.group(2).strip()
|
|
47
|
+
# Find matching closing brace
|
|
48
|
+
brace_start = m.end()
|
|
49
|
+
depth = 1
|
|
50
|
+
i = brace_start
|
|
51
|
+
while i < len(content) and depth > 0:
|
|
52
|
+
if content[i] == '{':
|
|
53
|
+
depth += 1
|
|
54
|
+
elif content[i] == '}':
|
|
55
|
+
depth -= 1
|
|
56
|
+
i += 1
|
|
57
|
+
body = content[brace_start:i - 1]
|
|
58
|
+
|
|
59
|
+
entry = {"cite_key": cite_key, "type": entry_type}
|
|
60
|
+
|
|
61
|
+
# Extract fields: key = {value} or key = "value" (handles nested braces)
|
|
62
|
+
field_re = re.compile(r"(\w+)\s*=\s*", re.IGNORECASE)
|
|
63
|
+
fpos = 0
|
|
64
|
+
while fpos < len(body):
|
|
65
|
+
fm = field_re.search(body, fpos)
|
|
66
|
+
if not fm:
|
|
67
|
+
break
|
|
68
|
+
key = fm.group(1).lower()
|
|
69
|
+
val_start = fm.end()
|
|
70
|
+
if val_start < len(body) and body[val_start] == '{':
|
|
71
|
+
depth = 1
|
|
72
|
+
j = val_start + 1
|
|
73
|
+
while j < len(body) and depth > 0:
|
|
74
|
+
if body[j] == '{':
|
|
75
|
+
depth += 1
|
|
76
|
+
elif body[j] == '}':
|
|
77
|
+
depth -= 1
|
|
78
|
+
j += 1
|
|
79
|
+
value = body[val_start + 1:j - 1]
|
|
80
|
+
fpos = j
|
|
81
|
+
elif val_start < len(body) and body[val_start] == '"':
|
|
82
|
+
end_q = body.find('"', val_start + 1)
|
|
83
|
+
if end_q == -1:
|
|
84
|
+
break
|
|
85
|
+
value = body[val_start + 1:end_q]
|
|
86
|
+
fpos = end_q + 1
|
|
87
|
+
else:
|
|
88
|
+
m_num = re.match(r"[^,}\s]+", body[val_start:])
|
|
89
|
+
if m_num:
|
|
90
|
+
value = m_num.group(0)
|
|
91
|
+
fpos = val_start + m_num.end()
|
|
92
|
+
else:
|
|
93
|
+
break
|
|
94
|
+
entry[key] = value.strip()
|
|
95
|
+
|
|
96
|
+
if not require_doi or entry.get("doi"):
|
|
97
|
+
entries.append(entry)
|
|
98
|
+
|
|
99
|
+
pos = i
|
|
100
|
+
|
|
101
|
+
return entries
|
|
102
|
+
|
|
@@ -0,0 +1,143 @@
|
|
|
1
|
+
"""BibTeX generation from Crossref metadata."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
import re
|
|
6
|
+
import urllib.parse
|
|
7
|
+
from typing import Any
|
|
8
|
+
|
|
9
|
+
from ..network import fetch_json
|
|
10
|
+
|
|
11
|
+
|
|
12
|
+
def fetch_bibtex(doi: str, config: dict[str, Any]) -> str | None:
|
|
13
|
+
"""Fetch BibTeX entry for a DOI from Crossref."""
|
|
14
|
+
q = urllib.parse.quote(doi, safe="")
|
|
15
|
+
url = f"https://api.crossref.org/works/{q}"
|
|
16
|
+
try:
|
|
17
|
+
payload = fetch_json(url, config, headers={"Accept": "application/json"})
|
|
18
|
+
if not payload:
|
|
19
|
+
return None
|
|
20
|
+
msg = payload.get("message", {})
|
|
21
|
+
return _crossref_to_bibtex(msg, doi)
|
|
22
|
+
except Exception:
|
|
23
|
+
return None
|
|
24
|
+
|
|
25
|
+
|
|
26
|
+
def _crossref_to_bibtex(msg: dict[str, Any], doi: str) -> str | None:
|
|
27
|
+
entry_type = _detect_entry_type(msg.get("type", ""))
|
|
28
|
+
if not entry_type:
|
|
29
|
+
entry_type = "article"
|
|
30
|
+
|
|
31
|
+
cite_key = _make_cite_key(msg, doi)
|
|
32
|
+
fields: dict[str, str] = {}
|
|
33
|
+
|
|
34
|
+
# Title
|
|
35
|
+
titles = msg.get("title", [])
|
|
36
|
+
if titles:
|
|
37
|
+
fields["title"] = _clean(titles[0])
|
|
38
|
+
|
|
39
|
+
# Authors
|
|
40
|
+
authors = msg.get("author", [])
|
|
41
|
+
if authors:
|
|
42
|
+
names = []
|
|
43
|
+
for a in authors:
|
|
44
|
+
family = a.get("family", "")
|
|
45
|
+
given = a.get("given", "")
|
|
46
|
+
if family and given:
|
|
47
|
+
names.append(f"{family}, {given}")
|
|
48
|
+
elif family:
|
|
49
|
+
names.append(family)
|
|
50
|
+
if names:
|
|
51
|
+
fields["author"] = " and ".join(names)
|
|
52
|
+
|
|
53
|
+
# Journal/Booktitle
|
|
54
|
+
container = msg.get("container-title", [])
|
|
55
|
+
if container:
|
|
56
|
+
fields["journal"] = _clean(container[0])
|
|
57
|
+
|
|
58
|
+
# Year
|
|
59
|
+
parts = msg.get("published-print", msg.get("published-online", msg.get("created", {})))
|
|
60
|
+
date_parts = parts.get("date-parts", [[]]) if isinstance(parts, dict) else [[]]
|
|
61
|
+
if date_parts and date_parts[0]:
|
|
62
|
+
fields["year"] = str(date_parts[0][0])
|
|
63
|
+
|
|
64
|
+
# Volume, Issue, Pages
|
|
65
|
+
if msg.get("volume"):
|
|
66
|
+
fields["volume"] = str(msg["volume"])
|
|
67
|
+
if msg.get("issue"):
|
|
68
|
+
fields["number"] = str(msg["issue"])
|
|
69
|
+
if msg.get("page"):
|
|
70
|
+
fields["pages"] = msg["page"].replace("-", "--")
|
|
71
|
+
|
|
72
|
+
# DOI
|
|
73
|
+
fields["doi"] = doi
|
|
74
|
+
|
|
75
|
+
# URL
|
|
76
|
+
fields["url"] = f"https://doi.org/{doi}"
|
|
77
|
+
|
|
78
|
+
# Publisher
|
|
79
|
+
if msg.get("publisher"):
|
|
80
|
+
fields["publisher"] = _clean(msg["publisher"])
|
|
81
|
+
|
|
82
|
+
# Abstract
|
|
83
|
+
if msg.get("abstract"):
|
|
84
|
+
fields["abstract"] = _clean(msg["abstract"])
|
|
85
|
+
|
|
86
|
+
return _format_bibtex(entry_type, cite_key, fields)
|
|
87
|
+
|
|
88
|
+
|
|
89
|
+
def _detect_entry_type(crossref_type: str) -> str:
|
|
90
|
+
mapping = {
|
|
91
|
+
"journal-article": "article",
|
|
92
|
+
"proceedings-article": "inproceedings",
|
|
93
|
+
"book-chapter": "incollection",
|
|
94
|
+
"book": "book",
|
|
95
|
+
"monograph": "book",
|
|
96
|
+
"edited-book": "book",
|
|
97
|
+
"reference-book": "book",
|
|
98
|
+
"dissertation": "phdthesis",
|
|
99
|
+
"report": "techreport",
|
|
100
|
+
"posted-content": "misc",
|
|
101
|
+
"proceedings": "proceedings",
|
|
102
|
+
}
|
|
103
|
+
return mapping.get(crossref_type, "article")
|
|
104
|
+
|
|
105
|
+
|
|
106
|
+
def _make_cite_key(msg: dict[str, Any], doi: str) -> str:
|
|
107
|
+
authors = msg.get("author", [])
|
|
108
|
+
first_author = ""
|
|
109
|
+
if authors:
|
|
110
|
+
first_author = authors[0].get("family", authors[0].get("given", ""))
|
|
111
|
+
first_author = re.sub(r"[^A-Za-z]", "", first_author)[:6]
|
|
112
|
+
|
|
113
|
+
parts = msg.get("published-print", msg.get("published-online", msg.get("created", {})))
|
|
114
|
+
date_parts = parts.get("date-parts", [[]]) if isinstance(parts, dict) else [[]]
|
|
115
|
+
year = str(date_parts[0][0]) if date_parts and date_parts[0] else "XXXX"
|
|
116
|
+
|
|
117
|
+
titles = msg.get("title", [])
|
|
118
|
+
first_word = ""
|
|
119
|
+
if titles:
|
|
120
|
+
words = re.findall(r"[A-Za-z]+", titles[0])
|
|
121
|
+
if words:
|
|
122
|
+
first_word = words[0][:6]
|
|
123
|
+
|
|
124
|
+
if not (first_author or first_word):
|
|
125
|
+
# Crossref gave us no author and no title: a bare "xxxx" key would
|
|
126
|
+
# collide with every other such entry, so lean on the DOI instead.
|
|
127
|
+
return re.sub(r"[^A-Za-z0-9]+", "_", doi).strip("_").lower() or "ref"
|
|
128
|
+
return f"{first_author}{year}{first_word}".lower()
|
|
129
|
+
|
|
130
|
+
|
|
131
|
+
def _clean(text: str) -> str:
|
|
132
|
+
text = re.sub(r"<[^>]+>", "", text)
|
|
133
|
+
text = text.replace("&", r"\&").replace("%", r"\%").replace("_", r"\_")
|
|
134
|
+
text = text.replace("{", r"\{").replace("}", r"\}")
|
|
135
|
+
return text.strip()
|
|
136
|
+
|
|
137
|
+
|
|
138
|
+
def _format_bibtex(entry_type: str, cite_key: str, fields: dict[str, str]) -> str:
|
|
139
|
+
lines = [f"@{entry_type}{{{cite_key},"]
|
|
140
|
+
for key, value in fields.items():
|
|
141
|
+
lines.append(f" {key} = {{{value}}},")
|
|
142
|
+
lines.append("}")
|
|
143
|
+
return "\n".join(lines)
|
|
@@ -0,0 +1,225 @@
|
|
|
1
|
+
"""Citation export in multiple formats (BibTeX, RIS, EndNote)."""
|
|
2
|
+
|
|
3
|
+
from __future__ import annotations
|
|
4
|
+
|
|
5
|
+
import re
|
|
6
|
+
from typing import Any
|
|
7
|
+
|
|
8
|
+
from ..network import fetch_json
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
def fetch_metadata(doi: str, config: dict[str, Any]) -> dict[str, Any] | None:
|
|
12
|
+
"""Fetch paper metadata from Crossref API."""
|
|
13
|
+
import urllib.parse
|
|
14
|
+
q = urllib.parse.quote(doi, safe="")
|
|
15
|
+
url = f"https://api.crossref.org/works/{q}"
|
|
16
|
+
try:
|
|
17
|
+
payload = fetch_json(url, config, headers={"Accept": "application/json"})
|
|
18
|
+
if not payload:
|
|
19
|
+
return None
|
|
20
|
+
return payload.get("message", {})
|
|
21
|
+
except Exception:
|
|
22
|
+
return None
|
|
23
|
+
|
|
24
|
+
|
|
25
|
+
def _extract_fields(msg: dict[str, Any], doi: str) -> dict[str, str]:
|
|
26
|
+
"""Extract common fields from Crossref metadata."""
|
|
27
|
+
fields: dict[str, str] = {}
|
|
28
|
+
|
|
29
|
+
# Title
|
|
30
|
+
titles = msg.get("title", [])
|
|
31
|
+
if titles:
|
|
32
|
+
fields["title"] = _clean_html(titles[0])
|
|
33
|
+
|
|
34
|
+
# Authors
|
|
35
|
+
authors = msg.get("author", [])
|
|
36
|
+
if authors:
|
|
37
|
+
fields["authors"] = authors
|
|
38
|
+
|
|
39
|
+
# Journal
|
|
40
|
+
container = msg.get("container-title", [])
|
|
41
|
+
if container:
|
|
42
|
+
fields["journal"] = _clean_html(container[0])
|
|
43
|
+
|
|
44
|
+
# Year
|
|
45
|
+
parts = msg.get("published-print", msg.get("published-online", msg.get("created", {})))
|
|
46
|
+
date_parts = parts.get("date-parts", [[]]) if isinstance(parts, dict) else [[]]
|
|
47
|
+
if date_parts and date_parts[0]:
|
|
48
|
+
fields["year"] = str(date_parts[0][0])
|
|
49
|
+
|
|
50
|
+
# Volume, Issue, Pages
|
|
51
|
+
if msg.get("volume"):
|
|
52
|
+
fields["volume"] = str(msg["volume"])
|
|
53
|
+
if msg.get("issue"):
|
|
54
|
+
fields["issue"] = str(msg["issue"])
|
|
55
|
+
if msg.get("page"):
|
|
56
|
+
fields["pages"] = msg["page"]
|
|
57
|
+
|
|
58
|
+
fields["doi"] = doi
|
|
59
|
+
fields["url"] = f"https://doi.org/{doi}"
|
|
60
|
+
|
|
61
|
+
if msg.get("publisher"):
|
|
62
|
+
fields["publisher"] = _clean_html(msg["publisher"])
|
|
63
|
+
|
|
64
|
+
if msg.get("abstract"):
|
|
65
|
+
fields["abstract"] = _clean_html(msg["abstract"])
|
|
66
|
+
|
|
67
|
+
# Entry type
|
|
68
|
+
type_mapping = {
|
|
69
|
+
"journal-article": "JOUR",
|
|
70
|
+
"proceedings-article": "CONF",
|
|
71
|
+
"book-chapter": "CHAP",
|
|
72
|
+
"book": "BOOK",
|
|
73
|
+
"monograph": "BOOK",
|
|
74
|
+
"dissertation": "THES",
|
|
75
|
+
"report": "RPRT",
|
|
76
|
+
"posted-content": "UNPB",
|
|
77
|
+
}
|
|
78
|
+
fields["entry_type"] = type_mapping.get(msg.get("type", ""), "JOUR")
|
|
79
|
+
|
|
80
|
+
return fields
|
|
81
|
+
|
|
82
|
+
|
|
83
|
+
def _clean_html(text: str) -> str:
|
|
84
|
+
text = re.sub(r"<[^>]+>", "", text)
|
|
85
|
+
return text.strip()
|
|
86
|
+
|
|
87
|
+
|
|
88
|
+
def _format_authors_ris(authors: list[dict]) -> list[str]:
|
|
89
|
+
"""Format authors for RIS format."""
|
|
90
|
+
result = []
|
|
91
|
+
for a in authors:
|
|
92
|
+
family = a.get("family", "")
|
|
93
|
+
given = a.get("given", "")
|
|
94
|
+
if family:
|
|
95
|
+
result.append(f"{family}, {given}".strip(", "))
|
|
96
|
+
return result
|
|
97
|
+
|
|
98
|
+
|
|
99
|
+
def to_ris(doi: str, config: dict[str, Any]) -> str | None:
|
|
100
|
+
"""Generate RIS format citation."""
|
|
101
|
+
msg = fetch_metadata(doi, config)
|
|
102
|
+
if not msg:
|
|
103
|
+
return None
|
|
104
|
+
return _metadata_to_ris(msg, doi)
|
|
105
|
+
|
|
106
|
+
|
|
107
|
+
def _metadata_to_ris(msg: dict[str, Any], doi: str) -> str:
|
|
108
|
+
fields = _extract_fields(msg, doi)
|
|
109
|
+
lines = []
|
|
110
|
+
|
|
111
|
+
# Type
|
|
112
|
+
lines.append(f"TY - {fields.get('entry_type', 'JOUR')}")
|
|
113
|
+
|
|
114
|
+
# Authors
|
|
115
|
+
authors = fields.get("authors", [])
|
|
116
|
+
for a in _format_authors_ris(authors):
|
|
117
|
+
lines.append(f"AU - {a}")
|
|
118
|
+
|
|
119
|
+
# Title
|
|
120
|
+
if "title" in fields:
|
|
121
|
+
lines.append(f"TI - {fields['title']}")
|
|
122
|
+
|
|
123
|
+
# Journal
|
|
124
|
+
if "journal" in fields:
|
|
125
|
+
lines.append(f"JO - {fields['journal']}")
|
|
126
|
+
|
|
127
|
+
# Year
|
|
128
|
+
if "year" in fields:
|
|
129
|
+
lines.append(f"PY - {fields['year']}")
|
|
130
|
+
|
|
131
|
+
# Volume
|
|
132
|
+
if "volume" in fields:
|
|
133
|
+
lines.append(f"VL - {fields['volume']}")
|
|
134
|
+
|
|
135
|
+
# Issue
|
|
136
|
+
if "issue" in fields:
|
|
137
|
+
lines.append(f"IS - {fields['issue']}")
|
|
138
|
+
|
|
139
|
+
# Pages
|
|
140
|
+
if "pages" in fields:
|
|
141
|
+
pages = fields["pages"]
|
|
142
|
+
if "-" in pages:
|
|
143
|
+
parts = pages.split("-", 1)
|
|
144
|
+
lines.append(f"SP - {parts[0].strip()}")
|
|
145
|
+
lines.append(f"EP - {parts[1].strip()}")
|
|
146
|
+
else:
|
|
147
|
+
lines.append(f"SP - {pages}")
|
|
148
|
+
|
|
149
|
+
# DOI
|
|
150
|
+
lines.append(f"DO - {doi}")
|
|
151
|
+
|
|
152
|
+
# URL
|
|
153
|
+
lines.append(f"UR - https://doi.org/{doi}")
|
|
154
|
+
|
|
155
|
+
# Publisher
|
|
156
|
+
if "publisher" in fields:
|
|
157
|
+
lines.append(f"PB - {fields['publisher']}")
|
|
158
|
+
|
|
159
|
+
# Abstract
|
|
160
|
+
if "abstract" in fields:
|
|
161
|
+
lines.append(f"AB - {fields['abstract']}")
|
|
162
|
+
|
|
163
|
+
lines.append("ER - ")
|
|
164
|
+
return "\n".join(lines)
|
|
165
|
+
|
|
166
|
+
|
|
167
|
+
def to_endnote(doi: str, config: dict[str, Any]) -> str | None:
|
|
168
|
+
"""Generate EndNote format citation."""
|
|
169
|
+
msg = fetch_metadata(doi, config)
|
|
170
|
+
if not msg:
|
|
171
|
+
return None
|
|
172
|
+
return _metadata_to_endnote(msg, doi)
|
|
173
|
+
|
|
174
|
+
|
|
175
|
+
def _metadata_to_endnote(msg: dict[str, Any], doi: str) -> str:
|
|
176
|
+
fields = _extract_fields(msg, doi)
|
|
177
|
+
lines = []
|
|
178
|
+
|
|
179
|
+
# Type
|
|
180
|
+
lines.append(f"%0 {fields.get('entry_type', 'JOUR')}")
|
|
181
|
+
|
|
182
|
+
# Authors
|
|
183
|
+
authors = fields.get("authors", [])
|
|
184
|
+
for a in _format_authors_ris(authors):
|
|
185
|
+
lines.append(f"%A {a}")
|
|
186
|
+
|
|
187
|
+
# Title
|
|
188
|
+
if "title" in fields:
|
|
189
|
+
lines.append(f"%T {fields['title']}")
|
|
190
|
+
|
|
191
|
+
# Journal
|
|
192
|
+
if "journal" in fields:
|
|
193
|
+
lines.append(f"%J {fields['journal']}")
|
|
194
|
+
|
|
195
|
+
# Year
|
|
196
|
+
if "year" in fields:
|
|
197
|
+
lines.append(f"%D {fields['year']}")
|
|
198
|
+
|
|
199
|
+
# Volume
|
|
200
|
+
if "volume" in fields:
|
|
201
|
+
lines.append(f"%V {fields['volume']}")
|
|
202
|
+
|
|
203
|
+
# Issue
|
|
204
|
+
if "issue" in fields:
|
|
205
|
+
lines.append(f"%N {fields['issue']}")
|
|
206
|
+
|
|
207
|
+
# Pages
|
|
208
|
+
if "pages" in fields:
|
|
209
|
+
lines.append(f"%P {fields['pages']}")
|
|
210
|
+
|
|
211
|
+
# DOI
|
|
212
|
+
lines.append(f"%R {doi}")
|
|
213
|
+
|
|
214
|
+
# URL
|
|
215
|
+
lines.append(f"%U https://doi.org/{doi}")
|
|
216
|
+
|
|
217
|
+
# Publisher
|
|
218
|
+
if "publisher" in fields:
|
|
219
|
+
lines.append(f"%I {fields['publisher']}")
|
|
220
|
+
|
|
221
|
+
# Abstract
|
|
222
|
+
if "abstract" in fields:
|
|
223
|
+
lines.append(f"%X {fields['abstract']}")
|
|
224
|
+
|
|
225
|
+
return "\n".join(lines)
|