aboutsummaryrefslogtreecommitdiff
path: root/backend/data
diff options
context:
space:
mode:
Diffstat (limited to 'backend/data')
-rw-r--r--backend/data/README.md6
-rwxr-xr-xbackend/data/genEnwikiNameData.py2
-rwxr-xr-xbackend/data/genEolNameData.py4
3 files changed, 5 insertions, 7 deletions
diff --git a/backend/data/README.md b/backend/data/README.md
index 19005e5..0bde721 100644
--- a/backend/data/README.md
+++ b/backend/data/README.md
@@ -49,21 +49,19 @@ File Generation Process
8 Run genLinkedImgs.py to add a 'linked_imgs' table to data.db,
which uses 'nodes', 'edges', 'eol\_ids', and 'node_imgs', to associate
nodes without images to child images.
-
5 Reduced Tree Structure Data
1 Run genReducedTreeData.py, which adds 'r_nodes' and 'r_edges' tables to
data.db, using reducedTol/names.txt, and the 'nodes' and 'names' tables.
6 Other
- 1 Can run genEnwikiNameData.py, which adds more entries to the 'names' table,
+ - Optionally run genEnwikiNameData.py, which adds more entries to the 'names' table,
using data in enwiki/enwikiData.db, and the 'names' and 'descs' tables.
- 2 //node-trimming
data.db Tables
==============
- nodes: name TEXT PRIMARY KEY, id TEXT UNIQUE, tips INT
- edges: node TEXT, child TEXT, p\_support INT, PRIMARY KEY (node, child)
- eol\_ids: id INT PRIMARY KEY, name TEXT
-- names: name TEXT, alt\_name TEXT, pref\_alt INT, PRIMARY KEY(name, alt\_name)
+- names: name TEXT, alt\_name TEXT, pref\_alt INT, src TEXT, PRIMARY KEY(name, alt\_name)
- descs: name TEXT PRIMARY KEY, desc TEXT, redirected INT, wiki\_id INT, from\_dbp INT
- images: id INT, src TEXT, url TEXT, license TEXT, artist TEXT, credit TEXT, PRIMARY KEY (id, src)
- node\_imgs: id TEXT PRIMARY KEY, img\_id INT, src TEXT
diff --git a/backend/data/genEnwikiNameData.py b/backend/data/genEnwikiNameData.py
index b5d8670..1beb522 100755
--- a/backend/data/genEnwikiNameData.py
+++ b/backend/data/genEnwikiNameData.py
@@ -64,7 +64,7 @@ print(f"Left with {numAltNames} alt-names")
print("Adding alt-names")
for (nodeName, altNames) in nodeToAltNames.items():
for altName in altNames:
- dbCur.execute("INSERT INTO names VALUES (?, ?, ?)", (nodeName, altName, 0))
+ dbCur.execute("INSERT INTO names VALUES (?, ?, ?, 'enwiki')", (nodeName, altName, 0))
# Close dbs
dbCon.commit()
dbCon.close()
diff --git a/backend/data/genEolNameData.py b/backend/data/genEolNameData.py
index 1b80dd8..74b0e3d 100755
--- a/backend/data/genEolNameData.py
+++ b/backend/data/genEolNameData.py
@@ -76,7 +76,7 @@ print(f"Found {len(nameToPickedPid)}")
dbCon = sqlite3.connect(dbFile)
dbCur = dbCon.cursor()
# Create tables
-dbCur.execute("CREATE TABLE names(name TEXT, alt_name TEXT, pref_alt INT, PRIMARY KEY(name, alt_name))")
+dbCur.execute("CREATE TABLE names(name TEXT, alt_name TEXT, pref_alt INT, src TEXT, PRIMARY KEY(name, alt_name))")
dbCur.execute("CREATE INDEX names_alt_idx ON names(alt_name)")
dbCur.execute("CREATE INDEX names_alt_idx_nc ON names(alt_name COLLATE NOCASE)")
dbCur.execute("CREATE TABLE eol_ids(id INT PRIMARY KEY, name TEXT)")
@@ -94,7 +94,7 @@ def addToDb(nodeName, pidToUse):
altNames.add(n)
for n in altNames:
isPreferred = 1 if (n == preferredName) else 0
- dbCur.execute("INSERT INTO names VALUES (?, ?, ?)", (nodeName, n, isPreferred))
+ dbCur.execute("INSERT INTO names VALUES (?, ?, ?, 'eol')", (nodeName, n, isPreferred))
for name in nameToPickedPid: # Add manually-picked pids
pickedPid = nameToPickedPid[name]
usedPids.add(pickedPid)