](http://opencitations.net)
[](https://github.com/opencitations/oc_api/actions/workflows/run_tests.yml)
-
+[](https://opencitations.github.io/oc_api/coverage/)
This repository contains the API service for OpenCitations, allowing users to interact with the OpenCitations datasets through RESTful endpoints.
@@ -140,37 +140,14 @@ You can customize the Gunicorn server configuration by modifying the `gunicorn.c
### Running Tests Locally
-To run the API tests locally, you'll need to have the test environment set up properly. The tests require a Virtuoso database to be running.
+The tests require Docker. Pytest fixtures in `test/conftest.py` automatically start and stop the QLever and Virtuoso containers.
-#### Prerequisites
-
-1. Install dependencies using uv:
-```bash
- uv sync --dev
-```
-
-2. Start the test database:
+1. Install dependencies:
```bash
- ./test/start_test_db.sh
+uv sync --dev
```
-#### Running the Tests
-
-Once the test database is running, you can execute the tests with coverage:
+2. Run the tests:
```bash
-# Run tests with coverage report
uv run pytest --cov=src --cov-report=term-missing --cov-report=html
-
-# Run only specific test files
-uv run pytest test/test_metaapi.py
-
-# Run tests with verbose output
-uv run pytest -v
-```
-
-#### Stopping the Test Database
-
-After running the tests, stop the test database:
-```bash
-./test/stop_test_db.sh
```
\ No newline at end of file
diff --git a/api_oc.py b/api_oc.py
index 1597522..9b12e9e 100644
--- a/api_oc.py
+++ b/api_oc.py
@@ -1,17 +1,16 @@
import web
import os
import json
-#from src.wl import WebLogger
import requests
import urllib.parse as urlparse
import re
import csv
-from urllib.parse import parse_qs, unquote
+from urllib.parse import unquote
from rdflib.plugins.sparql.parser import parseUpdate
import subprocess
import sys
import argparse
-from src.ramose import APIManager, Operation, HTMLDocumentationHandler
+from ramose import APIManager, Operation, HTMLDocumentationHandler
from io import StringIO
from redis import Redis
@@ -70,21 +69,6 @@
)
-# Set the web logger
-# web_logger = WebLogger(env_config["base_url"], env_config["log_dir"], [
-# "HTTP_X_FORWARDED_FOR", # The IP address of the client
-# "REMOTE_ADDR", # The IP address of internal balancer
-# "HTTP_USER_AGENT", # The browser type of the visitor
-# "HTTP_REFERER", # The URL of the page that called your program
-# "HTTP_HOST", # The hostname of the page being attempted
-# "REQUEST_URI", # The interpreted pathname of the requested document
-# # or CGI (relative to the document root)
-# "HTTP_AUTHORIZATION", # Access token
-# ],
-# # comment this line only for test purposes
-# {"REMOTE_ADDR": ["130.136.130.1", "130.136.2.47", "127.0.0.1"]}
-# )
-
# API Managers
meta_api_manager = APIManager(c["api_meta"], endpoint_override=env_config["sparql_endpoint_meta"])
meta_doc_manager = HTMLDocumentationHandler(meta_api_manager)
@@ -97,7 +81,7 @@
render = web.template.render(c["html"], globals={
'str': str,
'isinstance': isinstance,
- 'render': lambda *args, **kwargs: render(*args, **kwargs)
+ 'render': lambda *args, **kwargs: render(*args, **kwargs) # type: ignore[operator]
})
# common folder
@@ -108,7 +92,7 @@
def notfound_custom():
"""Custom 404 page"""
- return web.notfound(render_common.notfound(web.ctx.home + web.ctx.fullpath))
+ return web.notfound(render_common.notfound(web.ctx.home + web.ctx.fullpath)) # type: ignore[operator]
# App Web.py
app = web.application(urls, globals())
@@ -155,8 +139,8 @@ def validateAccessToken():
return True
auth_code = web.ctx.env.get('HTTP_AUTHORIZATION')
- if not auth_code is None:
- val = rconn.get(auth_code)
+ if auth_code is not None:
+ val: bytes | None = rconn.get(auth_code) # type: ignore[assignment]
if val is None or val.decode('utf-8') != auth_code:
raise web.HTTPError("403", {"Content-Type": "text/plain"}, "Invalid token. Remove the authorization HEADER or register a new token at https://opencitations.net/accesstoken")
return True
@@ -198,7 +182,7 @@ def POST(self):
class Header:
def GET(self):
current_subdomain = web.ctx.host.split('.')[0].lower()
- return render.header(sp_title="", current_subdomain=current_subdomain)
+ return render.header(sp_title="", current_subdomain=current_subdomain) # type: ignore[operator]
class Static:
def GET(self, name):
@@ -249,8 +233,7 @@ def POST(self):
if "application/x-www-form-urlencoded" in content_type:
return self.__run_query_string(active["sparql"], cur_data, True, content_type)
elif "application/sparql-query" in content_type:
- isupdate = None
- isupdate, sanitizedQuery = self.__is_update_query(cur_data)
+ isupdate, _ = self.__is_update_query(cur_data)
if not isupdate:
return self.__contact_tp(cur_data, True, content_type)
else:
@@ -296,22 +279,19 @@ def __is_update_query(self, query):
except Exception:
return False, query
- def __run_query_string(self, active, query_string, is_post=False,
- content_type="application/x-www-form-urlencoded"):
- # Add redirect if no query string is provided
+ def __run_query_string(self, _active: str, query_string: str, is_post: bool = False,
+ content_type: str = "application/x-www-form-urlencoded") -> str:
if query_string is None or query_string.strip() == "":
raise web.seeother('/')
-
+
parsed_query = urlparse.parse_qs(query_string)
- current_subdomain = web.ctx.host.split('.')[0].lower()
for k in self.collparam:
if k in parsed_query:
query = parsed_query[k][0]
- isupdate = None
- isupdate, sanitizedQuery = self.__is_update_query(query)
+ isupdate, _ = self.__is_update_query(query)
- if isupdate != None:
+ if isupdate is not None:
if isupdate:
raise web.HTTPError(
"403 ",
@@ -333,7 +313,7 @@ class Main:
def GET(self):
#web_logger.mes()
current_subdomain = web.ctx.host.split('.')[0].lower()
- return render.api(active="", sp_title="", sparql_endpoint="", current_subdomain=current_subdomain, render=render)
+ return render.api(active="", sp_title="", sparql_endpoint="", current_subdomain=current_subdomain, render=render) # type: ignore[operator]
class SparqlIndex(Sparql):
def __init__(self):
@@ -348,7 +328,7 @@ def __init__(self):
class Api:
- def OPTIONS(self, dataset, call):
+ def OPTIONS(self, _dataset: str, _call: str) -> None:
# remember to remove the slash at the end
org_ref = web.ctx.env.get('HTTP_REFERER')
if org_ref is not None:
@@ -364,6 +344,7 @@ def OPTIONS(self, dataset, call):
def GET(self, dataset, call):
validateAccessToken()
man = None
+ doc = None
if dataset == "":
raise web.redirect("/")
@@ -378,8 +359,7 @@ def GET(self, dataset, call):
man = meta_api_manager
doc = meta_doc_manager
-
- if man is None:
+ if man is None or doc is None:
raise web.notfound()
else:
if re.match("^/v[1-9]*/?$", call):
@@ -436,7 +416,7 @@ def GET(self, dataset, call):
next(csv.DictReader(f)), ensure_ascii=False)
raise web.HTTPError(
str(status_code)+" ", {"Content-Type": content_type}, mes)
- except:
+ except Exception:
raise web.HTTPError(
str(status_code)+" ", {"Content-Type": content_type}, str(res))
else:
diff --git a/pyproject.toml b/pyproject.toml
index e9c0a45..f6d21ca 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
[project]
name = "oc-api"
-version = "2.2.2"
+version = "2.3.0"
description = "OpenCitations API"
authors = [
{name = "Mario Petrella", email = "mario.petrella@unibo.it"},
@@ -9,7 +9,7 @@ authors = [
]
license = {text = "ISC"}
readme = "README.md"
-requires-python = ">=3.9,<3.12"
+requires-python = ">=3.10,<3.13"
dependencies = [
"apscheduler==3.10.1",
"astroid>=3.3.11",
@@ -41,13 +41,13 @@ dependencies = [
"python-lsp-jsonrpc>=1.1.2",
"python-lsp-server>=1.12.2",
"pytz>=2026.1.post1",
- "ramose>=1.0.8",
+ "ramose>=2.0.0",
"rdflib>=6.1.1",
"rdflib-jsonld>=0.6.2",
"redis>=7.0.1",
"requests>=2.32.4",
"rope>=1.14.0",
- "six>=1.13.0",
+ "six>=1.16.0",
"snowballstemmer>=3.0.1",
"sparqlwrapper>=2.0.0",
"toml>=0.10.2",
@@ -62,9 +62,11 @@ dependencies = [
[dependency-groups]
dev = [
+ "pyright>=1.1.408",
"pytest>=8.4.1",
"pytest-cov>=6.2.1",
- "virtuoso-utilities>=1.0.0",
+ "qlever>=0.5.45",
+ "ruff>=0.15.5",
]
[tool.pytest.ini_options]
diff --git a/src/api/index_v1.hf b/src/api/index_v1.hf
index 553ee52..7cae845 100644
--- a/src/api/index_v1.hf
+++ b/src/api/index_v1.hf
@@ -128,6 +128,7 @@ WHERE {
LIMIT 200000
+
#url /citations/{doi}
#type operation
#doi str(10\..+)
diff --git a/src/api/indexapi_common.py b/src/api/indexapi_common.py
new file mode 100644
index 0000000..89eb694
--- /dev/null
+++ b/src/api/indexapi_common.py
@@ -0,0 +1,209 @@
+import json
+import os
+from requests import RequestException, post
+from json import loads
+from datetime import datetime
+from dateutil.relativedelta import relativedelta
+
+with open("conf.json") as f:
+ c = json.load(f)
+
+env_config = {
+ "base_url": os.getenv("BASE_URL", c["base_url"]),
+ "sparql_endpoint_index": os.getenv("SPARQL_ENDPOINT_INDEX", c["sparql_endpoint_index"]),
+ "sparql_endpoint_meta": os.getenv("SPARQL_ENDPOINT_META", c["sparql_endpoint_meta"]),
+ "sync_enabled": os.getenv("SYNC_ENABLED", "false").lower() == "true"
+}
+
+
+def lower(s):
+ return s.lower(),
+
+
+def br_meta_metadata(values):
+ sparql_endpoint = env_config["sparql_endpoint_meta"]
+
+ sparql_query = """
+ PREFIX pro: %s" % (p, p_type, p_shape))
- result += "\n* [%s](#%s): %s" % (op["url"],
- op["url"], op["description"].split("\n")[0])
- ops += """Accepted HTTP method(s) %s
-Parameter(s) %s
-Result fields type%s
-Example%s
-Exemplar output (in JSON)
-%s"+self.clean_log(l, api_url) - + "
" for l in clean_list if self.clean_log(l, api_url) != '']) - api_title = api_dict["conf_json"][0]["title"] - html += """ - -