Release Text Tools 0.2.0

2026-09-02 07:24:52 +02:00
parent c69bd5af12
commit 5e962ff0f3
29 changed files with 1093 additions and 102 deletions
@@ -1,8 +1,8 @@
 import { useState } from "react";
 import {
-  decodeText,
  encodeText,
  triggerBlobDownload,
+  triggerBlobDownloads,
  type TextEncoding,
 } from "@add-ideas/toolbox-helpers";
 import {
@@ -13,6 +13,11 @@ import {
  type StepType,
  type TransformStep,
 } from "../text/pipeline";
+import {
+  createTextArtifactEvidence,
+  decodeTextWithEvidence,
+  type TextByteEvidence,
+} from "../text/evidence";

 const initial = "  Crème brûlée  \r\nAlpha\nalpha\r\n  Cedar  \n";
 const initialSteps: TransformStep[] = [
@@ -31,8 +36,16 @@ const STEP_LABELS: Record<StepType, string> = {
  normalize: "Unicode normalization",
  transliterate: "Best-effort transliteration",
  escape: "Escape / encode",
+  unescape: "Decode / unescape strictly",
  wrap: "Wrap text",
  columns: "Select/reorder columns",
+  "replace-literal": "Replace literal text",
+  "prefix-lines": "Prefix lines",
+  "suffix-lines": "Suffix lines",
+  "filter-lines": "Keep matching lines",
+  "number-lines": "Number lines",
+  "join-lines": "Join lines",
+  "reverse-lines": "Reverse line order",
 };

 function Option({
@@ -43,9 +56,13 @@ function Option({
  change: (option: string) => void;
 }) {
  if (
-    ["trim-lines", "trim-document", "dedupe-lines", "transliterate"].includes(
-      step.type,
-    )
+    [
+      "trim-lines",
+      "trim-document",
+      "dedupe-lines",
+      "transliterate",
+      "reverse-lines",
+    ].includes(step.type)
  )
    return <span className="muted">No options</span>;
  if (step.type === "line-endings")
@@ -104,10 +121,10 @@ function Option({
        ))}
      </select>
    );
-  if (step.type === "escape")
+  if (step.type === "escape" || step.type === "unescape")
    return (
      <select
-        aria-label="Escape target"
+        aria-label={step.type === "escape" ? "Escape target" : "Decode source"}
        value={step.option}
        onChange={(event) => change(event.target.value)}
      >
@@ -136,13 +153,89 @@ function Option({
        onChange={(event) => change(event.target.value)}
      />
    );
+  if (step.type === "replace-literal") {
+    let values: [string, string] = ["", ""];
+    try {
+      const parsed = JSON.parse(step.option) as unknown;
+      if (
+        Array.isArray(parsed) &&
+        parsed.length === 2 &&
+        parsed.every((value) => typeof value === "string")
+      )
+        values = parsed as [string, string];
+    } catch {
+      /* Keep editable empty values; apply will report invalid stored JSON. */
+    }
+    return (
+      <div className="column-options">
+        <input
+          aria-label="Literal search text"
+          value={values[0]}
+          onChange={(event) =>
+            change(JSON.stringify([event.target.value, values[1]]))
+          }
+        />
+        <input
+          aria-label="Literal replacement text"
+          value={values[1]}
+          onChange={(event) =>
+            change(JSON.stringify([values[0], event.target.value]))
+          }
+        />
+      </div>
+    );
+  }
+  if (
+    [
+      "prefix-lines",
+      "suffix-lines",
+      "filter-lines",
+      "number-lines",
+      "join-lines",
+    ].includes(step.type)
+  )
+    return (
+      <input
+        aria-label={`${STEP_LABELS[step.type]} option`}
+        value={step.option}
+        onChange={(event) => change(event.target.value)}
+        placeholder={
+          step.type === "join-lines"
+            ? "Delimiter; \\n and \\t supported"
+            : "Text"
+        }
+      />
+    );
+  const pieces = step.option.split("|");
+  const mode = pieces.length >= 3 ? pieces[0]! : "literal";
+  const delimiter = pieces.length >= 3 ? pieces[1]! : pieces[0] || ",";
+  const order =
+    pieces.length >= 3 ? pieces.slice(2).join("|") : pieces[1] || "1";
+  const encode = (nextMode: string, nextDelimiter: string, nextOrder: string) =>
+    change(`${nextMode}|${nextDelimiter}|${nextOrder}`);
  return (
-    <input
-      aria-label="Column settings"
-      value={step.option}
-      onChange={(event) => change(event.target.value)}
-      placeholder=",|3,1,2"
-    />
+    <div className="column-options">
+      <select
+        aria-label="Column parsing mode"
+        value={mode}
+        onChange={(event) => encode(event.target.value, delimiter, order)}
+      >
+        <option value="csv">Quoted CSV records</option>
+        <option value="literal">Literal delimiter per line</option>
+      </select>
+      <input
+        aria-label="Column delimiter"
+        value={delimiter}
+        onChange={(event) => encode(mode, event.target.value, order)}
+        placeholder=", or \\t"
+      />
+      <input
+        aria-label="Column order"
+        value={order}
+        onChange={(event) => encode(mode, delimiter, event.target.value)}
+        placeholder="3,1,2"
+      />
+    </div>
  );
 }

@@ -188,6 +281,8 @@ export function Workbench() {
  const [fatalDecode, setFatalDecode] = useState(true);
  const [error, setError] = useState("");
  const [recipe, setRecipe] = useState("");
+  const [sourceEvidence, setSourceEvidence] = useState<TextByteEvidence>();
+  const [sourceName, setSourceName] = useState("pasted-text.txt");
  const outputLoss =
    outputEncoding === "latin1" &&
    [...result.output].some((character) => character.codePointAt(0)! > 255);
@@ -218,16 +313,18 @@ export function Workbench() {
      return;
    }
    try {
-      const decoded = decodeText(
+      const decoded = decodeTextWithEvidence(
        new Uint8Array(await file.arrayBuffer()),
        inputEncoding,
        fatalDecode,
      );
-      if (decoded.length > 2_000_000)
+      if (decoded.text.length > 2_000_000)
        throw new Error(
          "Decoded text exceeds the 2,000,000 UTF-16-unit pipeline limit.",
        );
-      setSource(decoded);
+      setSource(decoded.text);
+      setSourceEvidence(decoded.evidence);
+      setSourceName(file.name);
      setError("");
    } catch (reason) {
      setError(
@@ -253,7 +350,7 @@ export function Workbench() {
  };
  const exportRecipe = () => {
    const value = JSON.stringify(
-      { schemaVersion: 1, app: "text-tools", version: "0.1.0", steps },
+      { schemaVersion: 1, app: "text-tools", version: "0.2.0", steps },
      null,
      2,
    );
@@ -263,6 +360,41 @@ export function Workbench() {
      "text-tools-recipe.json",
    );
  };
+  const exportArtifact = async () => {
+    try {
+      const bytes = encodeText(result.output, outputEncoding);
+      const evidence = await createTextArtifactEvidence({
+        sourceName,
+        sourceEvidence,
+        sourceText: source,
+        outputName: `transformed-${outputEncoding}.txt`,
+        outputEncoding,
+        outputBytes: bytes,
+        pipeline: result,
+        steps,
+      });
+      triggerBlobDownloads(
+        [
+          {
+            blob: new Blob([bytes as BlobPart], { type: "text/plain" }),
+            filename: evidence.output.name,
+          },
+          {
+            blob: new Blob([JSON.stringify(evidence, null, 2) + "\n"], {
+              type: "application/json",
+            }),
+            filename: "text-tools-artifact-evidence.json",
+          },
+        ],
+        { maximumFiles: 2, order: "input", revokeDelayMs: 1_000 },
+      );
+      setError("");
+    } catch (reason) {
+      setError(
+        reason instanceof Error ? reason.message : "Artifact export failed.",
+      );
+    }
+  };
  const importRecipe = () => {
    try {
      if (recipe.length > 1_000_000)
@@ -315,7 +447,8 @@ export function Workbench() {
          <h1>Text Tools</h1>
          <p>
            Build an ordered, visible transformation pipeline for normalization,
-            lines, casing, escaping, wrapping, and columns.
+            lines, casing, strict escaping/decoding, wrapping, and quoted or
+            literal-delimited columns.
          </p>
        </div>
        <span className="privacy-pill">Browser-local</span>
@@ -362,11 +495,54 @@ export function Workbench() {
          </div>
          <textarea
            value={source}
-            onChange={(event) => setSource(event.target.value)}
+            onChange={(event) => {
+              setSource(event.target.value);
+              setSourceEvidence(undefined);
+              setSourceName("pasted-text.txt");
+            }}
            spellCheck={false}
            aria-label="Text source"
          />
          <Inventory value={source} />
+          {sourceEvidence && (
+            <details>
+              <summary>Byte decoding evidence</summary>
+              <dl className="inventory">
+                <div>
+                  <dt>Selected / BOM</dt>
+                  <dd>
+                    {sourceEvidence.selectedEncoding} /{" "}
+                    {sourceEvidence.bom?.encoding ?? "none"}
+                  </dd>
+                </div>
+                <div>
+                  <dt>UTF-8 validation</dt>
+                  <dd>
+                    {sourceEvidence.utf8.valid
+                      ? "valid"
+                      : `invalid at byte ${sourceEvidence.utf8.firstInvalidOffset}`}
+                  </dd>
+                </div>
+                <div>
+                  <dt>Replacement characters</dt>
+                  <dd>{sourceEvidence.replacementCharacters}</dd>
+                </div>
+                <div>
+                  <dt>Byte newlines CRLF / LF / CR</dt>
+                  <dd>
+                    {sourceEvidence.byteNewlines.crlf} /{" "}
+                    {sourceEvidence.byteNewlines.bareLf} /{" "}
+                    {sourceEvidence.byteNewlines.bareCr}
+                  </dd>
+                </div>
+              </dl>
+              {sourceEvidence.warnings.map((warning) => (
+                <p className="warning" key={warning}>
+                  {warning}
+                </p>
+              ))}
+            </details>
+          )}
        </section>
        <section className="panel workspace" aria-labelledby="output-heading">
          <div className="panel-heading">
@@ -386,6 +562,9 @@ export function Workbench() {
              <button type="button" onClick={download}>
                Download
              </button>
+              <button type="button" onClick={() => void exportArtifact()}>
+                Export artifact + evidence
+              </button>
            </div>
          </div>
          <textarea
@@ -533,6 +712,7 @@ export function Workbench() {
          <summary>Versioned recipe import/export</summary>
          <div className="recipe">
            <textarea
+              aria-label="Text Tools recipe JSON"
              value={recipe}
              onChange={(event) => setRecipe(event.target.value)}
              placeholder="Paste a Text Tools recipe JSON here."
@@ -551,7 +731,12 @@ export function Workbench() {
          Encoding detection is limited to an explicit choice; no arbitrary
          charset guess is made. Transliteration, compatibility normalization,
          escaping, column omission, and narrow encodings can be lossy, so the
-          exact source and output remain visible.
+          exact source and output remain visible. Portable artifact evidence
+          includes exact hashes, selected encodings, newline facts and the
+          ordered recipe. SDK 0.3.0 provides the shared transfer contract, but
+          one-click Open With remains disabled until the Portal consumer rollout
+          is coordinated. This version provides explicit portable downloads in
+          the meantime.
        </p>
      </section>
    </main>