wut

2 files changed, 139 insertions, 0 deletions

diff --git a/packages/prosody-ui/src/thai/ThaiText.tsx b/packages/prosody-ui/src/thai/ThaiText.tsx
new file mode 100644
index 0000000..fc1e1e6
--- /dev/null
+++ b/packages/prosody-ui/src/thai/ThaiText.tsx
@@ -0,0 +1,49 @@
+import React, { useCallback, useEffect, useState } from "react";
+import "../assets/fonts/Thai/style.css";
+import { segmentateThai } from "./logic/thainlp";
+import type { AnalyzeRes } from "../logic/types";
+import { ColoredText } from "../components/Sentence";
+import Word from "../components/Word";
+
+export default function ThaiText({
+  text,
+  openWord,
+}: {
+  text: string;
+  openWord: (s: string) => void;
+}) {
+  useEffect(() => {
+    pythonseg();
+  }, [text]);
+
+  const [data, setData] = useState<Record<string, AnalyzeRes>>({});
+  const [modal, setModal] = useState<any>();
+  const pythonseg = useCallback(async () => {
+    const s2 = await segmentateThai(text.trim());
+    if ("ok" in s2) {
+      const ob = s2.ok.reduce((acc, item) => {
+        acc[item.word] = item;
+        return acc;
+      }, {} as any);
+      setData(ob);
+      console.log(s2, "s2");
+    } else console.error(s2.error);
+  }, [text]);
+
+  // function openWord(e: React.MouseEvent<any>) {
+  //   const s = e.currentTarget.innerText;
+  //   const d = data[s];
+  //   setModal(d);
+  //   // setModal(<WordModal data={d} lang={lang} />);
+  // }
+  return (
+    <div className="thaitext">
+      <ColoredText lang="tha" frags={Object.keys(data)} fn={openWord} />
+      {modal && <Word data={modal} lang={"tha"} />}
+    </div>
+  );
+}
+
+function ThaiWord() {
+  return <div />;
+}
diff --git a/packages/prosody-ui/src/thai/logic/thainlp.ts b/packages/prosody-ui/src/thai/logic/thainlp.ts
new file mode 100644
index 0000000..031bf4c
--- /dev/null
+++ b/packages/prosody-ui/src/thai/logic/thainlp.ts
@@ -0,0 +1,90 @@
+import type { AsyncRes } from "sortug";
+import type { AnalyzeRes } from "../../logic/types";
+
+const ENDPOINT = "http://192.168.1.110:8001";
+async function call(path: string, body: any) {
+  try {
+    const opts = {
+      method: "POST",
+      headers: { "Content-type": "application/json" },
+      body: JSON.stringify(body),
+    };
+    const r1 = await fetch(ENDPOINT + path, opts);
+    // const r2 = await fetch(`http://192.168.1.110:8000/analyze`, opts);
+    const jj = await r1.json();
+    return { ok: jj };
+  } catch (e) {
+    return { error: `${e}` };
+  }
+}
+export async function analyzeTHWord(word: string): AsyncRes<AnalyzeRes> {
+  return await call("/analyze", { word });
+}
+export async function segmentateThai(sentence: string): AsyncRes<AnalyzeRes[]> {
+  return await call("/segmentate", { word: sentence });
+}
+
+export const POSMAP: Record<string, string> = {
+  ADJ: "Adjective",
+  ADP: "Adposition",
+  ADV: "Adverb",
+  AUX: "Auxiliary",
+  CCONJ: "Coordinating conjunction",
+  DET: "Determiner",
+  INTJ: "Interjection",
+  NOUN: "Noun",
+  NUM: "Numeral",
+  PART: "Particle",
+  PRON: "Pronoun",
+  PROPN: "Proper noun",
+  PUNCT: "Punctuation",
+  SCONJ: "Subordinating conjunction",
+  VERB: "Verb",
+  NPRP: "Proper noun",
+  NCNM: "Cardinal number",
+  NONM: "Ordinal number",
+  NLBL: "Label noun",
+  NCMN: "Common noun",
+  NTTL: "Title noun",
+  PPRS: "Personal pronoun",
+  PDMN: "Demonstrative pronoun",
+  PNTR: "Interrogative pronoun",
+  PREL: "Relative pronoun",
+  VACT: "Active verb",
+  VSTA: "Stative verb",
+  VATT: "Attributive verb",
+  XVBM: "Pre-verb auxiliary, before negator “ไม่”",
+  XVAM: "Pre-verb auxiliary, after negator “ไม่”",
+  XVMM: "Pre-verb, before or after negator “ไม่”",
+  XVBB: "Pre-verb auxiliary, in imperative mood",
+  XVAE: "Post-verb auxiliary",
+  DDAN: "classifier in between",
+  DDAC: "in between",
+  DDBQ: "classifier or preceding quantitative expression",
+  DDAQ: "following quantitative expression",
+  DIAC: "classifier in between",
+  DIBQ: "classifier or preceding quantitative expression",
+  DIAQ: "following quantitative expression",
+  DCNM: "Determiner, cardinal number expression",
+  DONM: "Determiner, ordinal number expression",
+  ADVN: "Adverb with normal form",
+  ADVI: "Adverb with iterative form",
+  ADVP: "Adverb with prefixed form",
+  ADVS: "Sentential adverb",
+  CNIT: "Unit classifier",
+  CLTV: "Collective classifier",
+  CMTR: "Measurement classifier",
+  CFQC: "Frequency classifier",
+  CVBL: "Verbal classifier",
+  JCRG: "Coordinating conjunction",
+  JCMP: "Comparative conjunction",
+  JSBR: "Subordinating conjunction",
+  RPRE: "Preposition",
+  INT: "Interjection",
+  FIXN: "Nominal prefix",
+  FIXV: "Adverbial prefix",
+  EAFF: "Ending for affirmative sentence",
+  EITT: "Ending for interrogative sentence",
+  NEG: "Negator",
+  PUNC: "Punctuation",
+};