aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--backend/data/README.md1
-rwxr-xr-xbackend/data/dbpedia/genData.py26
-rwxr-xr-xbackend/data/downloadImgsForReview.py6
-rwxr-xr-xbackend/data/enwiki/genData.py10
-rwxr-xr-xbackend/data/enwiki/genDumpIndexDb.py8
-rwxr-xr-xbackend/data/enwiki/lookupPage.py4
-rwxr-xr-xbackend/data/genDbpConflicts.py16
-rwxr-xr-xbackend/data/genDbpData.py22
-rwxr-xr-xbackend/data/genEnwikiDescData.py8
-rwxr-xr-xbackend/data/genEnwikiNameData.py10
-rwxr-xr-xbackend/data/genEolNameData.py4
-rwxr-xr-xbackend/data/genImgsForWeb.py2
-rwxr-xr-xbackend/data/genLinkedImgs.py6
-rwxr-xr-xbackend/data/genOtolData.py12
-rwxr-xr-xbackend/data/genReducedTreeData.py16
-rwxr-xr-xbackend/data/reviewImgs.py15
-rwxr-xr-xbackend/server.py12
17 files changed, 89 insertions, 89 deletions
diff --git a/backend/data/README.md b/backend/data/README.md
index 4655c2d..f090898 100644
--- a/backend/data/README.md
+++ b/backend/data/README.md
@@ -1,6 +1,5 @@
File Generation Process
=======================
-
1 Tree Structure Data
1 Obtain data in otol/, as specified in it's README.
2 Run genOtolData.py, which creates data.db, and adds
diff --git a/backend/data/dbpedia/genData.py b/backend/data/dbpedia/genData.py
index 3df1961..7b48ac4 100755
--- a/backend/data/dbpedia/genData.py
+++ b/backend/data/dbpedia/genData.py
@@ -31,11 +31,11 @@ with bz2.open(labelsFile, mode='rt') as file:
for line in file:
lineNum += 1
if lineNum % 1e5 == 0:
- print("Processing line {}".format(lineNum))
+ print(f"Processing line {lineNum}")
#
match = labelLineRegex.fullmatch(line)
if match == None:
- print("ERROR: Line {} has unexpected format".format(lineNum), file=sys.stderr)
+ print(f"ERROR: Line {lineNum} has unexpected format", file=sys.stderr)
sys.exit(1)
else:
dbCur.execute("INSERT INTO labels VALUES (?, ?)", (match.group(1), match.group(2)))
@@ -49,18 +49,18 @@ with bz2.open(idsFile, mode='rt') as file:
for line in file:
lineNum += 1
if lineNum % 1e5 == 0:
- print("Processing line {}".format(lineNum))
+ print(f"Processing line {lineNum}")
#
match = idLineRegex.fullmatch(line)
if match == None:
- print("ERROR: Line {} has unexpected format".format(lineNum), file=sys.stderr)
+ print(f"ERROR: Line {lineNum} has unexpected format", file=sys.stderr)
sys.exit(1)
else:
try:
dbCur.execute("INSERT INTO ids VALUES (?, ?)", (match.group(1), int(match.group(2))))
except sqlite3.IntegrityError as e:
# Accounts for certain lines that have the same IRI
- print("Failed to add entry with IRI \"{}\": {}".format(match.group(1), e))
+ print(f"Failed to add entry with IRI \"{match.group(1)}\": {e}")
dbCon.commit()
# Read/store redirects
print("Reading/storing redirection data")
@@ -71,11 +71,11 @@ with bz2.open(redirectsFile, mode='rt') as file:
for line in file:
lineNum += 1
if lineNum % 1e5 == 0:
- print("Processing line {}".format(lineNum))
+ print(f"Processing line {lineNum}")
#
match = redirLineRegex.fullmatch(line)
if match == None:
- print("ERROR: Line {} has unexpected format".format(lineNum), file=sys.stderr)
+ print(f"ERROR: Line {lineNum} has unexpected format", file=sys.stderr)
sys.exit(1)
else:
dbCur.execute("INSERT INTO redirects VALUES (?, ?)", (match.group(1), match.group(2)))
@@ -89,11 +89,11 @@ with bz2.open(disambigFile, mode='rt') as file:
for line in file:
lineNum += 1
if lineNum % 1e5 == 0:
- print("Processing line {}".format(lineNum))
+ print(f"Processing line {lineNum}")
#
match = disambigLineRegex.fullmatch(line)
if match == None:
- print("ERROR: Line {} has unexpected format".format(lineNum), file=sys.stderr)
+ print(f"ERROR: Line {lineNum} has unexpected format", file=sys.stderr)
sys.exit(1)
else:
disambigNames.add(match.group(1))
@@ -111,11 +111,11 @@ with bz2.open(typesFile, mode='rt') as file:
for line in file:
lineNum += 1
if lineNum % 1e5 == 0:
- print("Processing line {}".format(lineNum))
+ print(f"Processing line {lineNum}")
#
match = typeLineRegex.fullmatch(line)
if match == None:
- print("ERROR: Line {} has unexpected format".format(lineNum), file=sys.stderr)
+ print(f"ERROR: Line {lineNum} has unexpected format", file=sys.stderr)
sys.exit(1)
else:
dbCur.execute("INSERT INTO types VALUES (?, ?)", (match.group(1), match.group(2)))
@@ -129,13 +129,13 @@ with bz2.open(abstractsFile, mode='rt') as file:
for line in file:
lineNum += 1
if lineNum % 1e5 == 0:
- print("Processing line {}".format(lineNum))
+ print(f"Processing line {lineNum}")
#
if line[0] == "#":
continue
match = descLineRegex.fullmatch(line)
if match == None:
- print("ERROR: Line {} has unexpected format".format(lineNum), file=sys.stderr)
+ print(f"ERROR: Line {lineNum} has unexpected format", file=sys.stderr)
sys.exit(1)
else:
dbCur.execute("INSERT INTO abstracts VALUES (?, ?)",
diff --git a/backend/data/downloadImgsForReview.py b/backend/data/downloadImgsForReview.py
index 5556fce..d1191d7 100755
--- a/backend/data/downloadImgsForReview.py
+++ b/backend/data/downloadImgsForReview.py
@@ -56,7 +56,7 @@ def downloadImg(url, outFile):
file.write(data.content)
time.sleep(random.random() * (POST_DL_DELAY_MAX - POST_DL_DELAY_MIN) + POST_DL_DELAY_MIN)
except Exception as e:
- print("Error while downloading to {}: {}".format(outFile, str(e)), file=sys.stderr)
+ print(f"Error while downloading to {outFile}: {str(e)}", file=sys.stderr)
threadException = e
numThreads -= 1
# Create output directory if not present
@@ -113,7 +113,7 @@ for idx in range(nextIdx, len(eolIds)):
urlParts = urllib.parse.urlparse(url)
extension = os.path.splitext(urlParts.path)[1]
if len(extension) <= 1:
- print("WARNING: No filename extension found in URL {}".format(url), file=sys.stderr)
+ print(f"WARNING: No filename extension found in URL {url}", file=sys.stderr)
continue
outFiles.append(str(eolId) + " " + str(contentId) + extension)
urls.append(url)
@@ -132,7 +132,7 @@ for idx in range(nextIdx, len(eolIds)):
time.sleep(1)
exitLoop = True
break
- print("Downloading image to {}".format(outPath))
+ print("Downloading image to {outPath}")
# Perform download
numThreads += 1
thread = Thread(target=downloadImg, args=(urls[i], outPath), daemon=True)
diff --git a/backend/data/enwiki/genData.py b/backend/data/enwiki/genData.py
index 646292c..f439d11 100755
--- a/backend/data/enwiki/genData.py
+++ b/backend/data/enwiki/genData.py
@@ -24,9 +24,9 @@ parensGrpRegex = re.compile(r" \([^()]*\)")
leftoverBraceRegex = re.compile(r"(?:{\||{{).*")
def convertTemplateReplace(match):
if match.group(2) == None:
- return "{} {}".format(match.group(1), match.group(4))
+ return f"{match.group(1)} {match.group(4)}"
else:
- return "{} {} {} {}".format(match.group(1), match.group(2), match.group(3), match.group(4))
+ return f"{match.group(1)} {match.group(2)} {match.group(3)} {match.group(4)}"
def parseDesc(text):
# Find first matching line outside a {{...}} and [[...]] block-html-comments, then accumulate lines until a blank
# Some cases not accounted for: disambiguation pages, abstracts with sentences split-across-lines,
@@ -83,7 +83,7 @@ def convertTitle(title):
# Check for existing db
if os.path.exists(enwikiDb):
- print("ERROR: Existing {}".format(enwikiDb), file=sys.stderr)
+ print(f"ERROR: Existing {enwikiDb}", file=sys.stderr)
sys.exit(1)
# Create db
dbCon = sqlite3.connect(enwikiDb)
@@ -101,14 +101,14 @@ with bz2.open(dumpFile, mode='rt') as file:
for page in dump:
pageNum += 1
if pageNum % 1e4 == 0:
- print("At page {}".format(pageNum))
+ print(f"At page {pageNum}")
# Parse page
if page.namespace == 0:
try:
dbCur.execute("INSERT INTO pages VALUES (?, ?)", (page.id, convertTitle(page.title)))
except sqlite3.IntegrityError as e:
# Accounts for certain pages that have the same title
- print("Failed to add page with title \"{}\": {}".format(page.title, e))
+ print(f"Failed to add page with title \"{page.title}\": {e}")
continue
if page.redirect != None:
dbCur.execute("INSERT INTO redirects VALUES (?, ?)", (page.id, convertTitle(page.redirect)))
diff --git a/backend/data/enwiki/genDumpIndexDb.py b/backend/data/enwiki/genDumpIndexDb.py
index 13f7eb6..450754b 100755
--- a/backend/data/enwiki/genDumpIndexDb.py
+++ b/backend/data/enwiki/genDumpIndexDb.py
@@ -16,7 +16,7 @@ indexDb = "dumpIndex.db"
# Check for existing db
if os.path.exists(indexDb):
- print("ERROR: Existing {}".format(indexDb), file=sys.stderr)
+ print(f"ERROR: Existing {indexDb}", file=sys.stderr)
sys.exit(1)
# Create db
dbCon = sqlite3.connect(indexDb)
@@ -31,7 +31,7 @@ with bz2.open(indexFile, mode='rt') as file:
for line in file:
lineNum += 1
if lineNum % 1e5 == 0:
- print("At line {}".format(lineNum))
+ print(f"At line {lineNum}")
#
match = lineRegex.fullmatch(line.rstrip())
(offset, _, title) = match.group(1,2,3)
@@ -42,7 +42,7 @@ with bz2.open(indexFile, mode='rt') as file:
dbCur.execute("INSERT INTO offsets VALUES (?, ?, ?)", (t, lastOffset, offset))
except sqlite3.IntegrityError as e:
# Accounts for certain entries in the file that have the same title
- print("Failed on title \"{}\": {}".format(t, e))
+ print(f"Failed on title \"{t}\": {e}")
titlesToAdd = []
lastOffset = offset
titlesToAdd.append(title)
@@ -50,7 +50,7 @@ for title in titlesToAdd:
try:
dbCur.execute("INSERT INTO offsets VALUES (?, ?, ?)", (title, lastOffset, -1))
except sqlite3.IntegrityError as e:
- print("Failed on title \"{}\": {}".format(t, e))
+ print(f"Failed on title \"{t}\": {e}")
# Close db
dbCon.commit()
dbCon.close()
diff --git a/backend/data/enwiki/lookupPage.py b/backend/data/enwiki/lookupPage.py
index c795c35..1d379e7 100755
--- a/backend/data/enwiki/lookupPage.py
+++ b/backend/data/enwiki/lookupPage.py
@@ -26,7 +26,7 @@ if row == None:
sys.exit(0)
(_, pageOffset, endOffset) = row
dbCon.close()
-print("Found chunk at offset {}".format(pageOffset))
+print(f"Found chunk at offset {pageOffset}")
# Read dump file
print("Reading dump file")
content = []
@@ -51,7 +51,7 @@ with open(dumpFile, mode='rb') as file:
titleLine = lines[lineIdx]
if titleLine.lstrip() == '<title>' + pageTitle + '</title>':
found = True
- print("Found title in chunk as page {}".format(pageNum))
+ print(f"Found title in chunk as page {pageNum}")
content.append(line)
content.append(titleLine)
while True:
diff --git a/backend/data/genDbpConflicts.py b/backend/data/genDbpConflicts.py
index 0ad4e1e..c0d3704 100755
--- a/backend/data/genDbpConflicts.py
+++ b/backend/data/genDbpConflicts.py
@@ -45,7 +45,7 @@ iterNum = 0
for (label,) in dbpCur.execute("SELECT label from labels"):
iterNum += 1
if iterNum % 1e5 == 0:
- print("Processing line {}".format(iterNum))
+ print(f"Processing line {iterNum}")
#
if label in disambigLabels:
continue
@@ -70,7 +70,7 @@ for (name, variants) in nameToVariants.items():
namesToRemove.add(name)
for name in namesToRemove:
del nameToVariants[name]
-print("Number of conflicts: {}".format(len(nameToVariants)))
+print(f"Number of conflicts: {len(nameToVariants)}")
# Try conflict resolution via taxon-type information
print("Resolving conflicts using instance-type data")
taxonTypes = { # Obtained from the DBpedia ontology
@@ -109,7 +109,7 @@ iterNum = 0
for (label, type) in dbpCur.execute("SELECT label, type from labels INNER JOIN types on labels.iri = types.iri"):
iterNum += 1
if iterNum % 1e5 == 0:
- print("Processing line {}".format(iterNum))
+ print(f"Processing line {iterNum}")
#
if type in taxonTypes:
name = label.lower()
@@ -121,7 +121,7 @@ for (label, type) in dbpCur.execute("SELECT label, type from labels INNER JOIN t
name = match.group(1)
if name in nameToVariants:
del nameToVariants[name]
-print("Number of conflicts: {}".format(len(nameToVariants)))
+print(f"Number of conflicts: {len(nameToVariants)}")
# Try conflict resolution via category-list
# Does a generic-category pass first (avoid stuff like Pan being classified as a horse instead of an ape)
print("Resolving conflicts using category-list")
@@ -163,7 +163,7 @@ for (name, variants) in nameToVariants.items():
break
for name in namesToRemove:
del nameToVariants[name]
-print("Number of conflicts: {}".format(len(nameToVariants)))
+print(f"Number of conflicts: {len(nameToVariants)}")
# Find descriptions for plain-named labels
print("Finding descriptions for plain-named labels")
labelToDesc = {}
@@ -172,7 +172,7 @@ query = "SELECT label, abstract from labels INNER JOIN abstracts ON labels.iri =
for (label, desc,) in dbpCur.execute(query):
iterNum += 1
if iterNum % 1e5 == 0:
- print("Processing line {}".format(iterNum))
+ print(f"Processing line {iterNum}")
#
if label.lower() in nameToVariants:
labelToDesc[label] = desc
@@ -183,7 +183,7 @@ query = "SELECT label, abstract from labels" \
for (label, desc,) in dbpCur.execute(query):
iterNum += 1
if iterNum % 1e5 == 0:
- print("Processing line {}".format(iterNum))
+ print(f"Processing line {iterNum}")
#
if label.lower() in nameToVariants:
labelToDesc[label] = desc
@@ -196,7 +196,7 @@ with open(outFile, "w") as file:
file.write("\n")
for n in variants:
if n in labelToDesc:
- file.write("\t{}: {}\n".format(n, labelToDesc[n]))
+ file.write(f"\t{n}: {labelToDesc[n]}\n")
# Close dbs
dbCon.close()
dbpCon.close()
diff --git a/backend/data/genDbpData.py b/backend/data/genDbpData.py
index c8394ea..0655344 100755
--- a/backend/data/genDbpData.py
+++ b/backend/data/genDbpData.py
@@ -41,7 +41,7 @@ iterNum = 0
for (label,) in dbpCur.execute("SELECT label from labels"):
iterNum += 1
if iterNum % 1e5 == 0:
- print("Processing line {}".format(iterNum))
+ print(f"Processing line {iterNum}")
#
if label in disambigLabels:
continue
@@ -66,7 +66,7 @@ for (name, variants) in nameToVariants.items():
for name in nodeToLabel:
del nameToVariants[name]
nodeToLabel["cellular organisms"] = "organism" # Special case for root node
-print("Number of conflicts: {}".format(len(nameToVariants)))
+print(f"Number of conflicts: {len(nameToVariants)}")
# Try conflict resolution via picked-labels
print("Resolving conflicts using picked-labels")
with open(pickedLabelsFile) as file:
@@ -79,15 +79,15 @@ with open(pickedLabelsFile) as file:
else:
match = nameVariantRegex.match(pickedLabel)
if match == None:
- print("WARNING: Picked label {} not found (1)".format(pickedLabel), file=sys.stderr)
+ print(f"WARNING: Picked label {pickedLabel} not found (1)", file=sys.stderr)
else:
name = match.group(1)
if name not in nameToVariants:
- print("WARNING: Picked label {} not found (2)".format(pickedLabel), file=sys.stderr)
+ print(f"WARNING: Picked label {pickedLabel} not found (2)", file=sys.stderr)
else:
nodeToLabel[name] = pickedLabel
del nameToVariants[name]
-print("Number of conflicts: {}".format(len(nameToVariants)))
+print(f"Number of conflicts: {len(nameToVariants)}")
# Try conflict resolution via category-list
# Does a generic-category pass first (avoid stuff like Pan being classified as a horse instead of an ape)
print("Resolving conflicts using category-list")
@@ -131,7 +131,7 @@ for (name, variants) in nameToVariants.items():
break
for name in namesToRemove:
del nameToVariants[name]
-print("Number of conflicts: {}".format(len(nameToVariants)))
+print(f"Number of conflicts: {len(nameToVariants)}")
# Try conflict resolution via taxon-type information
print("Resolving conflicts using instance-type data")
taxonTypes = { # Obtained from the DBpedia ontology
@@ -170,7 +170,7 @@ iterNum = 0
for (label, type) in dbpCur.execute("SELECT label, type from labels INNER JOIN types on labels.iri = types.iri"):
iterNum += 1
if iterNum % 1e5 == 0:
- print("Processing line {}".format(iterNum))
+ print(f"Processing line {iterNum}")
#
if type in taxonTypes:
name = label.lower()
@@ -184,7 +184,7 @@ for (label, type) in dbpCur.execute("SELECT label, type from labels INNER JOIN t
if name in nameToVariants:
nodeToLabel[name] = label
del nameToVariants[name]
-print("Number of conflicts: {}".format(len(nameToVariants)))
+print(f"Number of conflicts: {len(nameToVariants)}")
# Associate nodes with IRIs
print("Getting nodes IRIs")
nodeToIri = {}
@@ -192,7 +192,7 @@ iterNum = 0
for (name, label) in nodeToLabel.items():
row = dbpCur.execute("SELECT iri FROM labels where label = ? COLLATE NOCASE", (label,)).fetchone()
if row == None:
- print("ERROR: Couldn't find label {}".format(label), file=sys.stderr)
+ print(f"ERROR: Couldn't find label {label}", file=sys.stderr)
sys.exit(1)
else:
nodeToIri[name] = row[0]
@@ -203,7 +203,7 @@ iterNum = 0
for (name, iri) in nodeToIri.items():
iterNum += 1
if iterNum % 1e4 == 0:
- print("At iteration {}".format(iterNum))
+ print(f"At iteration {iterNum}")
#
row = dbpCur.execute("SELECT target FROM redirects where iri = ?", (iri,)).fetchone()
if row != None:
@@ -216,7 +216,7 @@ iterNum = 0
for (name, iri) in nodeToIri.items():
iterNum += 1
if iterNum % 1e4 == 0:
- print("At iteration {}".format(iterNum))
+ print(f"At iteration {iterNum}")
#
query = "SELECT abstract, id FROM abstracts INNER JOIN ids ON abstracts.iri = ids.iri WHERE ids.iri = ?"
row = dbpCur.execute(query, (iri,)).fetchone()
diff --git a/backend/data/genEnwikiDescData.py b/backend/data/genEnwikiDescData.py
index 40a6c92..57e4194 100755
--- a/backend/data/genEnwikiDescData.py
+++ b/backend/data/genEnwikiDescData.py
@@ -25,7 +25,7 @@ nodeNames = set()
query = "SELECT nodes.name FROM nodes LEFT JOIN descs ON nodes.name = descs.name WHERE desc IS NULL"
for row in dbCur.execute(query):
nodeNames.add(row[0])
-print("Found {} names".format(len(nodeNames)))
+print(f"Found {len(nodeNames)} names")
# Find page id for each node name
print("Getting node page-ids")
nodeToPageId = {}
@@ -33,7 +33,7 @@ iterNum = 0
for name in nodeNames:
iterNum += 1
if iterNum % 1e4 == 0:
- print("At iteration {}".format(iterNum))
+ print(f"At iteration {iterNum}")
#
row = enwikiCur.execute("SELECT id FROM pages WHERE pages.title = ? COLLATE NOCASE", (name,)).fetchone()
if row != None:
@@ -45,7 +45,7 @@ iterNum = 0
for (name, pageId) in nodeToPageId.items():
iterNum += 1
if iterNum % 1000 == 0:
- print("At iteration {}".format(iterNum))
+ print(f"At iteration {iterNum}")
#
row = enwikiCur.execute(
"SELECT pages.id FROM redirects INNER JOIN pages ON redirects.target = pages.title WHERE redirects.id = ?",
@@ -59,7 +59,7 @@ iterNum = 0
for (name, pageId) in nodeToPageId.items():
iterNum += 1
if iterNum % 1000 == 0:
- print("At iteration {}".format(iterNum))
+ print(f"At iteration {iterNum}")
#
row = enwikiCur.execute("SELECT desc FROM descs where descs.id = ?", (pageId,)).fetchone()
if row != None:
diff --git a/backend/data/genEnwikiNameData.py b/backend/data/genEnwikiNameData.py
index dfed46c..fd50338 100755
--- a/backend/data/genEnwikiNameData.py
+++ b/backend/data/genEnwikiNameData.py
@@ -25,7 +25,7 @@ print("Getting nodes with wiki IDs")
nodeToWikiId = {}
for row in dbCur.execute("SELECT name, wiki_id from descs"):
nodeToWikiId[row[0]] = row[1]
-print("Found {} nodes".format(len(nodeToWikiId)))
+print(f"Found {len(nodeToWikiId)} nodes")
# Find wiki-ids that redirect to each node
print("Finding redirecter names")
nodeToAltNames = {}
@@ -34,7 +34,7 @@ iterNum = 0
for (nodeName, wikiId) in nodeToWikiId.items():
iterNum += 1
if iterNum % 1e4 == 0:
- print("At iteration {}".format(iterNum))
+ print(f"At iteration {iterNum}")
#
nodeToAltNames[nodeName] = set()
query = "SELECT p1.title FROM pages p1" \
@@ -44,7 +44,7 @@ for (nodeName, wikiId) in nodeToWikiId.items():
if altNameRegex.fullmatch(name) != None:
nodeToAltNames[nodeName].add(name.lower())
numAltNames += 1
-print("Found {} alt-names".format(numAltNames))
+print(f"Found {numAltNames} alt-names")
# Remove existing alt-names
print("Removing existing alt-names")
query = "SELECT alt_name FROM names WHERE alt_name IN ({})"
@@ -52,14 +52,14 @@ iterNum = 0
for (nodeName, altNames) in nodeToAltNames.items():
iterNum += 1
if iterNum % 1e4 == 0:
- print("At iteration {}".format(iterNum))
+ print(f"At iteration {iterNum}")
#
existingNames = set()
for (name,) in dbCur.execute(query.format(",".join(["?"] * len(altNames))), list(altNames)):
existingNames.add(name)
numAltNames -= len(existingNames)
altNames.difference_update(existingNames)
-print("Left with {} alt-names".format(numAltNames))
+print(f"Left with {numAltNames} alt-names")
# Add alt-names
print("Adding alt-names")
for (nodeName, altNames) in nodeToAltNames.items():
diff --git a/backend/data/genEolNameData.py b/backend/data/genEolNameData.py
index fb91e8a..e7eccba 100755
--- a/backend/data/genEolNameData.py
+++ b/backend/data/genEolNameData.py
@@ -77,7 +77,7 @@ for row in dbCur2.execute("SELECT name FROM nodes"):
name = row[0]
iterationNum += 1
if iterationNum % 10000 == 0:
- print("Loop 1 iteration {}".format(iterationNum))
+ print(f"Loop 1 iteration {iterationNum}")
# If name matches a canonical-name, add alt-name entries to 'names' table
if name in canonicalNameToPids:
pidToUse = 0
@@ -103,7 +103,7 @@ iterationNum = 0
for name in unresolvedNodeNames:
iterationNum += 1
if iterationNum % 100 == 0:
- print("Loop 2 iteration {}".format(iterationNum))
+ print(f"Loop 2 iteration {iterationNum}")
# Add alt-name entries to 'names' table for first corresponding pid
pidToUse = 0
for pid in nameToPids[name]:
diff --git a/backend/data/genImgsForWeb.py b/backend/data/genImgsForWeb.py
index 91a1cde..9db260f 100755
--- a/backend/data/genImgsForWeb.py
+++ b/backend/data/genImgsForWeb.py
@@ -76,7 +76,7 @@ for i in range(inputImgIdx, len(inputImgList)):
imgName = inputImgList[i]
[eolIdStr, otherStr] = imgName.split(" ")
contentId = int(otherStr.split(".")[0])
- print("Converting {}".format(imgName))
+ print(f"Converting {imgName}")
subprocess.run(
['npx', 'smartcrop-cli',
'--width', str(IMG_OUT_SZ),
diff --git a/backend/data/genLinkedImgs.py b/backend/data/genLinkedImgs.py
index 2e3fdce..6e26ca4 100755
--- a/backend/data/genLinkedImgs.py
+++ b/backend/data/genLinkedImgs.py
@@ -27,7 +27,7 @@ query = "SELECT nodes.name, eol_ids.id FROM" \
" INNER JOIN images ON eol_ids.id = images.eol_id"
for (name, eolId) in dbCur.execute(query):
resolvedNodes[name] = eolId
-print("Got {} nodes".format(len(resolvedNodes)))
+print(f"Got {len(resolvedNodes)} nodes")
# Iterate through resolved nodes, resolving ancestors where able
print("Resolving ancestor nodes")
nodesToResolve = {}
@@ -37,7 +37,7 @@ iterNum = 0
while len(resolvedNodes) > 0:
iterNum += 1
if iterNum % 1e3 == 0:
- print("At iteration {}".format(iterNum))
+ print(f"At iteration {iterNum}")
# Get next node
(nodeName, eolId) = resolvedNodes.popitem()
processedNodes[nodeName] = eolId
@@ -85,7 +85,7 @@ iterNum = 0
for nodeName in processedNodes.keys():
iterNum += 1
if iterNum % 1e3 == 0:
- print("At iteration {}".format(iterNum))
+ print(f"At iteration {iterNum}")
#
match = compoundNameRegex.fullmatch(nodeName)
if match != None:
diff --git a/backend/data/genOtolData.py b/backend/data/genOtolData.py
index 87db2c4..2ea548a 100755
--- a/backend/data/genOtolData.py
+++ b/backend/data/genOtolData.py
@@ -131,13 +131,13 @@ def parseNewickName():
elif name[0] == "'":
match = re.fullmatch(r"'([^\\\"]+) (ott\d+)'", name)
if match == None:
- raise Exception("ERROR: invalid name \"{}\"".format(name))
+ raise Exception(f"ERROR: invalid name \"{name}\"")
name = match.group(1).replace("''", "'")
return [name, match.group(2)]
else:
match = re.fullmatch(r"([^\\\"]+)_(ott\d+)", name)
if match == None:
- raise Exception("ERROR: invalid name \"{}\"".format(name))
+ raise Exception(f"ERROR: invalid name \"{name}\"")
return [match.group(1).replace("_", " "), match.group(2)]
rootId = parseNewick()
# For nodes with *many* children, remove some of those children
@@ -148,8 +148,8 @@ if os.path.exists(keptNamesFile):
for line in file:
namesToKeep.add(line.rstrip())
else:
- print("WARNING: No '{}' file found".format(keptNamesFile))
-print("Read in {} nodes".format(len(namesToKeep)))
+ print(f"WARNING: No '{keptNamesFile}' file found")
+print(f"Read in {len(namesToKeep)} nodes")
keptAncestors = set()
for name in namesToKeep:
if name in nameToFirstId:
@@ -237,7 +237,7 @@ def convertMrcaName(id):
name = node["name"]
childIds = node["children"]
if len(childIds) < 2:
- print("WARNING: MRCA node \"{}\" has less than 2 children".format(name), file=sys.stderr)
+ print(f"WARNING: MRCA node \"{name}\" has less than 2 children", file=sys.stderr)
return
# Get 2 children with most tips
childTips = [nodeMap[id]["tips"] for id in childIds]
@@ -261,7 +261,7 @@ def convertMrcaName(id):
if match != None:
childName2 = match.group(1)
# Create composite name
- node["name"] = "[{} + {}]".format(childName1, childName2)
+ node["name"] = f"[{childName1} + {childName2}]"
return childName1
for [id, node] in nodeMap.items():
if node["name"].startswith("mrca"):
diff --git a/backend/data/genReducedTreeData.py b/backend/data/genReducedTreeData.py
index 9cdf1d6..a88573d 100755
--- a/backend/data/genReducedTreeData.py
+++ b/backend/data/genReducedTreeData.py
@@ -26,7 +26,7 @@ with open(nodeNamesFile) as file:
for line in file:
iterNum += 1
if iterNum % 100 == 0:
- print("Iteration {}".format(iterNum))
+ print(f"Iteration {iterNum}")
#
row = dbCur.execute("SELECT name from nodes WHERE name = ?", (line.rstrip(),)).fetchone()
if row == None:
@@ -36,7 +36,7 @@ with open(nodeNamesFile) as file:
if len(minimalNames) == 0:
print("ERROR: No names found", file=sys.stderr)
sys.exit(1)
-print("Name set has {} names".format(len(minimalNames)))
+print(f"Name set has {len(minimalNames)} names")
# Add nodes that connect up to root
print("Getting connected nodes set")
iterNum = 0
@@ -44,7 +44,7 @@ rootName = None
for name in minimalNames:
iterNum += 1
if iterNum % 100 == 0:
- print("Iteration {}".format(iterNum))
+ print(f"Iteration {iterNum}")
#
prevName = None
while name != None:
@@ -67,7 +67,7 @@ for name in minimalNames:
break
if name == None:
rootName = prevName
-print("New node set has {} nodes".format(len(nodeMap)))
+print(f"New node set has {len(nodeMap)} nodes")
# Remove certain 'chain collapsible' nodes
print("Removing 'chain collapsible' nodes")
namesToRemove = set()
@@ -85,7 +85,7 @@ for (name, nodeObj) in nodeMap.items():
namesToRemove.add(name)
for name in namesToRemove:
del nodeMap[name]
-print("New node set has {} nodes".format(len(nodeMap)))
+print(f"New node set has {len(nodeMap)} nodes")
# Merge-upward compsite-named nodes
print("Merging-upward composite-named nodes")
namesToRemove2 = set()
@@ -103,7 +103,7 @@ for (name, nodeObj) in nodeMap.items():
for name in namesToRemove2:
del nodeMap[name]
namesToRemove.add(name)
-print("New node set has {} nodes".format(len(nodeMap)))
+print(f"New node set has {len(nodeMap)} nodes")
# Add some connected children
print("Adding additional nearby children")
namesToAdd = []
@@ -111,7 +111,7 @@ iterNum = 0
for (name, nodeObj) in nodeMap.items():
iterNum += 1
if iterNum % 100 == 0:
- print("Iteration {}".format(iterNum))
+ print(f"Iteration {iterNum}")
#
numChildren = len(nodeObj["children"])
if numChildren < PREF_NUM_CHILDREN:
@@ -131,7 +131,7 @@ for name in namesToAdd:
"tips": 0,
"pSupport": pSupport == 1,
}
-print("New node set has {} nodes".format(len(nodeMap)))
+print(f"New node set has {len(nodeMap)} nodes")
# set tips vals
print("Setting tips vals")
def setTips(nodeName):
diff --git a/backend/data/reviewImgs.py b/backend/data/reviewImgs.py
index 037ef07..63e7dd5 100755
--- a/backend/data/reviewImgs.py
+++ b/backend/data/reviewImgs.py
@@ -135,11 +135,12 @@ class EolImgReviewer:
row = dbCur.execute(query, (self.nextEolId,)).fetchone()
if row != None:
commonName = row[1]
- self.root.title("Reviewing EOL ID {}, aka \"{}\" (imgs {} to {} out of {})".format(
- self.nextEolId, commonName, firstImgIdx, lastImgIdx, len(self.imgList)))
+ self.root.title(
+ f"Reviewing EOL ID {self.nextEolId}, aka \"{commonName}\"" \
+ f"(imgs {firstImgIdx} to {lastImgIdx} out of {len(self.imgList)})")
else:
- self.root.title("Reviewing EOL ID {} (imgs {} to {} out of {})".format(
- self.nextEolId, firstImgIdx, lastImgIdx, len(self.imgList)))
+ self.root.title(
+ f"Reviewing EOL ID {self.nextEolId} (imgs {firstImgIdx} to {lastImgIdx} out of {len(self.imgList)})")
def accept(self, imgIdx):
""" React to a user selecting an image """
if imgIdx >= len(self.nextImgNames):
@@ -173,11 +174,11 @@ class EolImgReviewer:
self.labels[imgIdx].config(image=self.photoImgs[imgIdx])
self.rotations[imgIdx] = (self.rotations[imgIdx] + deg) % 360
def quit(self, e = None):
- print("Number reviewed: {}".format(self.numReviewed))
+ print(f"Number reviewed: {self.numReviewed}")
timeElapsed = time.time() - self.startTime
- print("Time elapsed: {:.2f} seconds".format(timeElapsed))
+ print(f"Time elapsed: {timeElapsed:.2f} seconds")
if self.numReviewed > 0:
- print("Avg time per review: {:.2f} seconds".format(timeElapsed / self.numReviewed))
+ print(f"Avg time per review: {timeElapsed/self.numReviewed:.2f} seconds")
dbCon.close()
self.root.destroy()
def resizeForDisplay(self, img):
diff --git a/backend/server.py b/backend/server.py
index a712216..c564466 100755
--- a/backend/server.py
+++ b/backend/server.py
@@ -35,7 +35,7 @@ def lookupNodes(names, useReducedTree):
nodesTable = "nodes" if not useReducedTree else "r_nodes"
edgesTable = "edges" if not useReducedTree else "r_edges"
queryParamStr = ",".join(["?"] * len(names))
- query = "SELECT name, tips FROM {} WHERE name IN ({})".format(nodesTable, queryParamStr)
+ query = f"SELECT name, tips FROM {nodesTable} WHERE name IN ({queryParamStr})"
for (nodeName, tips) in cur.execute(query, names):
nodeObjs[nodeName] = {
"children": [],
@@ -45,10 +45,10 @@ def lookupNodes(names, useReducedTree):
"commonName": None,
"imgName": None,
}
- query = "SELECT node, child FROM {} WHERE node IN ({})".format(edgesTable, queryParamStr)
+ query = f"SELECT node, child FROM {edgesTable} WHERE node IN ({queryParamStr})"
for (nodeName, childName) in cur.execute(query, names):
nodeObjs[nodeName]["children"].append(childName)
- query = "SELECT node, child, p_support FROM {} WHERE child IN ({})".format(edgesTable, queryParamStr)
+ query = f"SELECT node, child, p_support FROM {edgesTable} WHERE child IN ({queryParamStr})"
for (nodeName, childName, pSupport) in cur.execute(query, names):
nodeObjs[childName]["parent"] = None if nodeName == "" else nodeName
nodeObjs[childName]["pSupport"] = (pSupport == 1)
@@ -72,7 +72,7 @@ def lookupNodes(names, useReducedTree):
str(eolId2) + ".jpg" if eolId2 != 0 else None,
]
# Get preferred-name info
- query = "SELECT name, alt_name FROM names WHERE pref_alt = 1 AND name IN ({})".format(queryParamStr)
+ query = f"SELECT name, alt_name FROM names WHERE pref_alt = 1 AND name IN ({queryParamStr})"
for (name, altName) in cur.execute(query, names):
if altName != name:
nodeObjs[name]["commonName"] = altName
@@ -185,7 +185,7 @@ class DbServer(BaseHTTPRequestHandler):
if not ranOnce:
self.respondJson(results)
return
- print("ERROR: Parent-chain node {} not found".format(name), file=sys.stderr)
+ print(f"ERROR: Parent-chain node {name} not found", file=sys.stderr)
break
nodeObj = nodeObjs[name]
results[name] = nodeObj
@@ -221,7 +221,7 @@ class DbServer(BaseHTTPRequestHandler):
self.wfile.write(json.dumps(val).encode("utf-8"))
server = HTTPServer((hostname, port), DbServer)
-print("Server started at http://{}:{}".format(hostname, port))
+print(f"Server started at http://{hostname}:{port}")
try:
server.serve_forever()
except KeyboardInterrupt:
generated by cgit v1.2.3 (git 2.39.1) at 2026-04-24 21:24:10 +0000