Skip to content

perf(resolver): short-circuit jargon and noise checks in quality scoring #547

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
d-oit wants to merge 1 commit into from
Closed

perf(resolver): short-circuit jargon and noise checks in quality scoring #547

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 12 additions & 4 deletions .agents/skills/do-web-doc-resolver/scripts/quality.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,8 +86,12 @@ def _check_jargon(text_lower: str) -> bool:
"transform",
"supercharge",
]
jargon_count = sum(text_lower.count(signal) for signal in jargon_signals)
return jargon_count > THRESHOLD_JARGON
jargon_count = 0
for signal in jargon_signals:
jargon_count += text_lower.count(signal)
if jargon_count > THRESHOLD_JARGON:
return True
return False


def _check_frontmatter(text: str) -> bool:
Expand Down Expand Up @@ -115,8 +119,12 @@ def _check_anchors(text: str) -> bool:
def _compute_noise(text_lower: str) -> bool:
"""Detect noisy signals like cookie/subscribe prompts."""
noisy_signals = ["cookie", "subscribe", "javascript", "log in", "sign up"]
noise_count = sum(text_lower.count(signal) for signal in noisy_signals)
return noise_count > THRESHOLD_NOISE
noise_count = 0
for signal in noisy_signals:
noise_count += text_lower.count(signal)
if noise_count > THRESHOLD_NOISE:
return True
return False


def is_bot_challenge(content: str) -> bool:
Expand Down
16 changes: 12 additions & 4 deletions scripts/quality.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,8 +86,12 @@ def _check_jargon(text_lower: str) -> bool:
"transform",
"supercharge",
]
jargon_count = sum(text_lower.count(signal) for signal in jargon_signals)
return jargon_count > THRESHOLD_JARGON
jargon_count = 0
for signal in jargon_signals:
jargon_count += text_lower.count(signal)
if jargon_count > THRESHOLD_JARGON:
return True
return False


def _check_frontmatter(text: str) -> bool:
Expand Down Expand Up @@ -115,8 +119,12 @@ def _check_anchors(text: str) -> bool:
def _compute_noise(text_lower: str) -> bool:
"""Detect noisy signals like cookie/subscribe prompts."""
noisy_signals = ["cookie", "subscribe", "javascript", "log in", "sign up"]
noise_count = sum(text_lower.count(signal) for signal in noisy_signals)
return noise_count > THRESHOLD_NOISE
noise_count = 0
for signal in noisy_signals:
noise_count += text_lower.count(signal)
if noise_count > THRESHOLD_NOISE:
return True
return False


def is_bot_challenge(content: str) -> bool:
Expand Down
Loading