Rewrite export.py, add diagram

.gitignore

@@ -5,7 +5,6 @@ __pycache__/
 captchas/
 _stats.json
 config.py
-db.sqlite3
 oddb.log
 praw.ini
 env/

database.py

@@ -242,7 +242,7 @@ class Database:
 
         return page
 
-    def join_website_on_scan(self, docs: list):
+    def join_website_url(self, docs):
 
         websites = self.get_all_websites()
 

export.py

@@ -1,39 +1,63 @@
-import csv
 import os
+import time
+
+import lz4.frame
 
 import config
 from database import Database
 from search.search import ElasticSearchEngine
 
 
-def export(outfile="out.csv"):
-
-    print("Export started, connecting to databases...")
-    es = ElasticSearchEngine("od-database")
-    db = Database(config.DB_CONN_STR)
-    docs = es.stream_all_docs()
-    docs_with_website = db.join_website_on_scan(docs)
-
-    print("Connected, writing to csv")
-
-    with open(outfile + ".temp", "w") as out:
-
-        csv_writer = csv.writer(out)
-        csv_writer.writerow(["website_id", "website_url", "path", "name", "ext", "size", "mtime"])
-
-        for doc in docs_with_website:
-            csv_writer.writerow([doc["_source"]["website_id"],
-                                 doc["_source"]["website_url"],
-                                 doc["_source"]["path"] + "/" if doc["_source"]["path"] != "" else "",
-                                 doc["_source"]["name"],
-                                 "." + doc["_source"]["ext"] if doc["_source"]["ext"] != "" else "",
-                                 doc["_source"]["size"],
-                                 doc["_source"]["mtime"]])
-    print("Wrote to csv, compressing with xz")
-
-    os.system("xz -0 " + outfile + ".temp")
-    os.system("mv " + outfile + ".temp.xz " + outfile + ".xz")
-    print("Compressed to " + str(os.path.getsize(outfile + ".xz")) + " bytes")
+def quote(string):
+    if "\"" in string:
+        return "\"" + string.replace("\"", "\"\"") + "\""
+    elif "," in string:
+        return "\"" + string + "\""
+    else:
+        return string
 
 
-export("static/out.csv")
+outfile = time.strftime("%Y-%m-%d_%H:%M:%S_dump.csv.lz4", time.gmtime())
+dldir = "static/downloads/"
+
+print("Deleting existing dumps")
+for file in os.listdir(dldir):
+    if file.endswith("_dump.csv.lz4"):
+        os.remove(os.path.join(dldir, file))
+
+print("Export started, connecting to databases...")
+
+db = Database(config.DB_CONN_STR)
+es = ElasticSearchEngine("od-database")
+
+docs_with_url = db.join_website_url(es.stream_all_docs())
+
+print("Connected, writing to csv")
+
+with lz4.frame.open(outfile + ".part", mode='wb',
+                    compression_level=9,
+                    block_size=lz4.frame.BLOCKSIZE_MAX4MB) as fp:
+    fp.write((",".join(
+        ["website_id", "website_url", "path", "name", "ext", "size", "mtime"]
+    ) + "\n").encode())
+
+    for doc in docs_with_url:
+        try:
+            fp.write(
+                (",".join(
+                    [
+                        str(doc["_source"]["website_id"]),
+                        quote(doc["_source"]["website_url"]),
+                        quote(doc["_source"]["path"]),
+                        quote(doc["_source"]["name"]),
+                        quote(doc["_source"]["ext"]),
+                        str(doc["_source"]["size"]),
+                        str(doc["_source"]["mtime"])
+                    ]
+                ) + "\n").encode())
+        except Exception as e:
+            print(e)
+            print(doc)
+
+
+os.rename(outfile + ".part", os.path.join(dldir, outfile))

requirements.txt

@@ -21,4 +21,5 @@ numpy
 matplotlib
 uwsgi
 redis
-psycopg2-binary
+psycopg2-binary
+lz4