[pt] More verbs/nouns fixes in disambiguation.xml #11095
Conversation
WalkthroughThe changes in this pull request introduce a new rule in the Changes
Possibly related issues
Possibly related PRs
Suggested reviewers
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Outside diff range and nitpick comments (1)
languagetool-language-modules/pt/src/main/resources/org/languagetool/resource/pt/disambiguation.xml (1)
3819-3824: Consider adding more specific token restrictions.The pattern could be more restrictive to avoid potential false positives. Consider adding specific exceptions for common cases where the past participle should retain its verb tag.
<token postag="N.+|AQ.+" postag_regexp="yes"><exception postag_regexp='yes' postag='V.+|CS|RG|CC|SPS.+|[DP].+'/></token> <token regexp='yes' spacebefore='no'>&hifen;</token> <marker> - <token spacebefore='no' postag='VMP00.+' postag_regexp="yes"/> + <token spacebefore='no' postag='VMP00.+' postag_regexp="yes"> + <exception regexp='yes'>estado|visto|feito|dito|posto</exception> + </token> </marker>
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
📒 Files selected for processing (1)
languagetool-language-modules/pt/src/main/resources/org/languagetool/resource/pt/disambiguation.xml(1 hunks)
🔇 Additional comments (3)
languagetool-language-modules/pt/src/main/resources/org/languagetool/resource/pt/disambiguation.xml (3)
3816-3836: LGTM! Well-structured new rule for handling hyphenated nouns with past participles.
The rule correctly handles cases like "peixe-DOURADO" by removing verb tags when a noun/adjective is followed by a hyphenated past participle. The pattern matching and examples are comprehensive.
3827-3835: Great documentation with examples!
The examples provided are comprehensive and clearly illustrate the rule's purpose. This will help future maintainers understand the intended behavior.
3816-3837: Verify rule ordering impact.
The placement of the new rule before PELA_COMO_SOBRE_NADA_ACERCA_ELAR_VERBS_RARE seems correct, but let's verify there are no unintended interactions.
✅ Verification successful
Based on the search results, I can see that there are no other rules in the disambiguation.xml file that handle hyphenated words with past participles in a way that would conflict with the NOUN_HYPHEN_PASTPARTICIPLE_VERBS_RARE rule. The rule's pattern is unique in how it specifically targets:
- A noun or adjective followed by
- A hyphen followed by
- A past participle verb form
Let me verify the order by searching for the referenced rule:
Rule ordering is correct and no conflicts found
The placement of NOUN_HYPHEN_PASTPARTICIPLE_VERBS_RARE before PELA_COMO_SOBRE_NADA_ACERCA_ELAR_VERBS_RARE is appropriate since:
- The rules have distinct patterns that don't overlap - one handles hyphenated constructs while the other handles past participles followed by specific words
- The examples in both rules demonstrate different use cases
- The rules have different disambiguation actions that don't interfere with each other
🏁 Scripts executed
The following scripts were executed for the analysis:
Script:
#!/bin/bash
# Description: Check for potential rule conflicts by looking for similar patterns
# in other disambiguation rules
# Search for rules that also handle past participles
rg -A 5 'postag=.VMP00.+.'
# Search for rules that handle hyphenated words
rg -A 5 '&hifen;'
Length of output: 68276
Script:
#!/bin/bash
# Search for the PELA_COMO_SOBRE_NADA_ACERCA_ELAR_VERBS_RARE rule and its context
rg -B 5 -A 5 'PELA_COMO_SOBRE_NADA_ACERCA_ELAR_VERBS_RARE'
Length of output: 1782
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Outside diff range and nitpick comments (1)
languagetool-language-modules/pt/src/main/resources/org/languagetool/resource/pt/disambiguation.xml (1)
3817-3818: Consider adding more context to the placement comment.The comment about moving the rule down could be more descriptive about why this placement is necessary, e.g., what specific rules it needs to work with.
- <!-- Moved the rule down to assure it works correctly. --> + <!-- Moved the rule down after other verb disambiguation rules to ensure correct processing order and avoid interference with verb pattern matching. -->
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
📒 Files selected for processing (1)
languagetool-language-modules/pt/src/main/resources/org/languagetool/resource/pt/disambiguation.xml(1 hunks)
🔇 Additional comments (2)
languagetool-language-modules/pt/src/main/resources/org/languagetool/resource/pt/disambiguation.xml (2)
3816-3827: LGTM! Well-structured disambiguation rule for hyphenated words.
The rule correctly handles the disambiguation of past participles in hyphenated compounds like "peixe-DOURADO", removing verb readings when they follow nouns/adjectives. The pattern matching and exceptions are comprehensive.
3828-3835: LGTM! Well-documented examples.
The examples effectively demonstrate various use cases for the rule, including different types of hyphenated compounds where past participles should not be interpreted as verbs.
|
It DIDN'T break Premium! |
More verbs/nouns fixes for words not in the dictionary: “peixe-DOURADO” (“dourado” would appear as a past participle).
Summary by CodeRabbit