Initial commit

.gitignore

@@ -0,0 +1,4 @@
+cachefile.doir
+index.html
+links/
+.idea/

Pipfile

@@ -0,0 +1,12 @@
+[[source]]
+name = "pypi"
+url = "https://pypi.org/simple"
+verify_ssl = true
+
+[dev-packages]
+
+[packages]
+habanero = "*"
+
+[requires]
+python_version = "3.8"

Pipfile.lock

@@ -0,0 +1,71 @@
+{
+    "_meta": {
+        "hash": {
+            "sha256": "703754edf167e2bedf149502d92a2b030f121676b4ee7dcf07db18d247316a26"
+        },
+        "pipfile-spec": 6,
+        "requires": {
+            "python_version": "3.8"
+        },
+        "sources": [
+            {
+                "name": "pypi",
+                "url": "https://pypi.org/simple",
+                "verify_ssl": true
+            }
+        ]
+    },
+    "default": {
+        "certifi": {
+            "hashes": [
+                "sha256:017c25db2a153ce562900032d5bc68e9f191e44e9a0f762f373977de9df1fbb3",
+                "sha256:25b64c7da4cd7479594d035c08c2d809eb4aab3a26e5a990ea98cc450c320f1f"
+            ],
+            "version": "==2019.11.28"
+        },
+        "chardet": {
+            "hashes": [
+                "sha256:84ab92ed1c4d4f16916e05906b6b75a6c0fb5db821cc65e70cbd64a3e2a5eaae",
+                "sha256:fc323ffcaeaed0e0a02bf4d117757b98aed530d9ed4531e3e15460124c106691"
+            ],
+            "version": "==3.0.4"
+        },
+        "habanero": {
+            "hashes": [
+                "sha256:b8494c0c600a5973e91ca6dc007781158a2799431d9c61888e095a2091a435df",
+                "sha256:d6b545384285b98b1577b0f88fd0da4cd59d550134776dd08f13188e77f3af88"
+            ],
+            "index": "pypi",
+            "version": "==0.7.2"
+        },
+        "idna": {
+            "hashes": [
+                "sha256:7588d1c14ae4c77d74036e8c22ff447b26d0fde8f007354fd48a7814db15b7cb",
+                "sha256:a068a21ceac8a4d63dbfd964670474107f541babbd2250d61922f029858365fa"
+            ],
+            "version": "==2.9"
+        },
+        "requests": {
+            "hashes": [
+                "sha256:43999036bfa82904b6af1d99e4882b560e5e2c68e5c4b0aa03b655f3d7d73fee",
+                "sha256:b3f43d496c6daba4493e7c431722aeb7dbc6288f52a6e04e7b6023b0247817e6"
+            ],
+            "version": "==2.23.0"
+        },
+        "tqdm": {
+            "hashes": [
+                "sha256:00339634a22c10a7a22476ee946bbde2dbe48d042ded784e4d88e0236eca5d81",
+                "sha256:ea9e3fd6bd9a37e8783d75bfc4c1faf3c6813da6bd1c3e776488b41ec683af94"
+            ],
+            "version": "==4.45.0"
+        },
+        "urllib3": {
+            "hashes": [
+                "sha256:2f3db8b19923a873b3e5256dc9c2dedfa883e33d87c690d9c7913e1f40673cdc",
+                "sha256:87716c2d2a7121198ebcb7ce7cccf6ce5e9ba539041cfbaeecfb641dc0bf6acc"
+            ],
+            "version": "==1.25.8"
+        }
+    },
+    "develop": {}
+}

doir.py

@@ -0,0 +1,131 @@
+import os.path
+import argparse
+from habanero import Crossref
+import json
+from datetime import datetime
+import http.server
+import socketserver
+
+parser = argparse.ArgumentParser()
+parser.add_argument("directory", help="directory which contains the files to resolve", type=str, default=".")
+parser.add_argument("cachefile", help="path to the cache file containing already resolved DOIs", type=str,
+                    default="cachefile.doir", nargs='?')
+parser.add_argument("htmlfile", help="path to the html result file", type=str, default="index.html", nargs='?')
+args = parser.parse_args()
+
+cr = Crossref()
+results = {}
+# Fifty days
+fifty_days = 60 * 60 * 24 * 50
+
+
+def query_crossref(doi, file):
+    result = cr.works(filter={"doi": doi})
+
+    if result['message']['total-results'] > 0:
+        title = result['message']['items'][0]['title'][0]
+        date_parts = result['message']['items'][0]['created']['date-parts']
+        date = str(date_parts[0][0]) + "-" + str(date_parts[0][1]) + "-" + str(date_parts[0][2])
+
+        return {'title': title, 'date': date, 'file_ref': file}
+
+
+# Expected directory structure is:
+#  [directory_arg]
+#    - 10.1145, organisation DOI prefix (e.g. for ACM)
+#       - 4547.4552.pdf, file name is the document DOI suffix
+#       - 361604.361612.pdf
+#       - ...
+#    - another prefix
+#       - more suffixes
+def walk_files(dir, prefix):
+    files = os.listdir(dir)
+
+    for file in files:
+        full_file = os.path.join(dir, file)
+
+        print("Process file: " + full_file)
+
+        if os.path.isdir(full_file):
+            walk_files(dir=full_file, prefix=file)
+        else:
+            doi_suffix = os.path.splitext(file)[0]
+            doi = prefix + "/" + doi_suffix
+            # Query the cache first
+            cached = doi in results
+
+            # Cache hit
+            if cached:
+                print("Cache hit!")
+
+                result = results[doi]
+                has_timestamp = 'timestamp' in result
+
+                if has_timestamp and (result['timestamp'] + fifty_days) > datetime.now().timestamp():
+                    # Cache result is older than 50 days
+                    # Query CrossRef again
+                    result = query_crossref(doi, 'links/' + prefix + "/" + file)
+
+                    # Not found again, create a new cache miss entry
+                    if result is None:
+                        result = {'timestamp': datetime.now().timestamp(), 'file_ref': 'links/' + prefix + "/" + file}
+            # Cache miss
+            else:
+                print("Cache miss!")
+
+                # Check whether CrossRef has metadata for this DOI
+                result = query_crossref(doi, 'links/' + prefix + "/" + file)
+
+                # If not, create a cache miss entry
+                if result is None:
+                    print("Not found!")
+
+                    result = {'timestamp': datetime.now().timestamp(), 'file_ref': 'links/' + prefix + "/" + file}
+
+            results[doi] = result
+
+
+def write_cache(file):
+    with open(file, 'w') as cache_file:
+        cache_file.write(json.dumps(results))
+
+
+def read_cache(file):
+    if os.path.isfile(file):
+        with open(file, 'r') as cache_file:
+            return json.loads(cache_file.read())
+    else:
+        return {}
+
+
+def write_html(file):
+    with open(file, 'w') as html_file:
+        html_file.write("<html><head></head><body><table><tr><th>Title</th><th>Year</th><th>Link</th></tr>")
+        for result in results:
+            html_file.write("<tr>")
+            if 'title' in results[result]:
+                html_file.write("<td>" + results[result]['title'] + "</td>")
+            else:
+                html_file.write("<td>No title!</td>")
+
+            if 'date' in results[result]:
+                html_file.write("<td>" + results[result]['date'] + "</td>")
+            else:
+                html_file.write("<td>No date!</td>")
+
+            html_file.write("<td><a href=\"" + results[result]['file_ref'] + "\">click</a></td>")
+            html_file.write("</tr>")
+
+        html_file.write("</table></body>")
+
+
+results = read_cache(file=args.cachefile)
+walk_files(dir=args.directory, prefix=None)
+write_cache(file=args.cachefile)
+write_html(file=args.htmlfile)
+
+os.symlink(args.directory, 'links')
+
+Handler = http.server.SimpleHTTPRequestHandler
+httpd = socketserver.TCPServer(("", 8888), Handler)
+httpd.serve_forever()