diff options
author | Vincent Ambo <mail@tazj.in> | 2023-01-18T00·22+0300 |
---|---|---|
committer | tazjin <tazjin@tvl.su> | 2023-01-18T01·10+0000 |
commit | 485c3cc912a5713a22cd655c0e35d77d686e3ccc (patch) | |
tree | 83f6b7550f02917461582c2918f0a29fde1fc33c /corp/russian/data-import/src/main.rs | |
parent | ee7616d9563eabf2ae01927bc9d37ccf3e3b3325 (diff) |
feat(corp/data-import): parse lemmas from OpenCorpora dump r/5684
Change-Id: I1e4efcfc8e555f61578b563411d5e6ed9590d8e8 Reviewed-on: https://cl.tvl.fyi/c/depot/+/7860 Reviewed-by: tazjin <tazjin@tvl.su> Tested-by: BuildkiteCI
Diffstat (limited to 'corp/russian/data-import/src/main.rs')
-rw-r--r-- | corp/russian/data-import/src/main.rs | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/corp/russian/data-import/src/main.rs b/corp/russian/data-import/src/main.rs index 336cc3d14f9f..9f2f5089a603 100644 --- a/corp/russian/data-import/src/main.rs +++ b/corp/russian/data-import/src/main.rs @@ -80,11 +80,11 @@ fn main() { let mut out = BufWriter::new(std::io::stdout().lock()); while let Some(elem) = parser.next_element() { - match elem { - oc_parser::OcElement::Grammeme(g) => { - writeln!(out, "{:?}", g).ensure("writing element failed") + if let oc_parser::OcElement::Lemma(lemma) = elem { + if lemma.lemma.word == "тяжёлый" { + writeln!(out, "{:?}", lemma).ensure("writing output failed"); + break; } - oc_parser::OcElement::Lemma(_) => continue, } } |