chore(ui): rename Upload → Import in user-facing strings

DataTools is local-first — "Upload" reads like "send data somewhere remote", which contradicts the product positioning. Sweep replaces the user-visible term throughout the UI: - ``src/i18n/packs/en.json`` + ``es.json``: all ``upload.*`` strings (heading, intro, uploader labels, empty state, switch-back, etc.) and ``gate.default_name``. The ``intro_multi`` "no upload anywhere" phrasing dropped the verb entirely — now reads "nothing leaves this computer". - All 9 tool pages: ``st.file_uploader(label="Upload …")`` → ``"Import …"``; matching ``st.info("Upload a …")`` empty-state banners; ``help="Upload …"`` strings on disabled uploaders. - ``9_Pipeline_Runner`` + ``5_Column_Mapper``: radio-option text ``"Upload schema/pipeline JSON"`` → ``"Import …"`` plus the ``.startswith("Upload")`` branch guards that read those values. - ``_home.py``: "**Uploaded files**" → "**Imported files**". - ``app_demo.py``: "Uploaded file is …" → "Imported file is …". Internal identifiers left untouched: function names (``pickup_or_upload``, ``_StashedUpload``), session-state keys (``home_upload``, ``home_uploads``, ``home_uploaded_*``, ``merger_file_upload``), audit-log event category (``"upload"``), Streamlit testid CSS selectors. None of those are visible to the user. The file_uploader's dropzone button text is a baked-in React literal that Streamlit's ``label=`` doesn't reach; rewritten at the DOM level with a small ``_RENAME_UPLOAD_BUTTON_JS`` snippet shipped through ``st.iframe`` (same pattern the sticky footer uses to mount on ``<body>``). A ``MutationObserver`` on the parent document re- applies the swap when Streamlit remounts the dropzone after file add/remove or page navigation, throttled via ``requestAnimationFrame``. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-18 23:48:31 +00:00
parent 3c4b80895e
commit 444dffbc63
14 changed files with 98 additions and 44 deletions
--- a/src/gui/_home.py
+++ b/src/gui/_home.py
@@ -156,7 +156,7 @@ def _home_page() -> None:
    #    interleaving widget-key updates with state changes.
    if home_uploads:
        import hashlib
-        st.markdown("**Uploaded files**")
+        st.markdown("**Imported files**")
        to_remove: str | None = None
        for name in list(home_uploads.keys()):
            digest = hashlib.sha1(
--- a/src/gui/app_demo.py
+++ b/src/gui/app_demo.py
@@ -239,7 +239,7 @@ def _read_uploaded(uploaded_file) -> tuple[pd.DataFrame, list[str]]:
    size_mb = len(raw) / 1024 / 1024
    if size_mb > DEMO_FILE_CAP_MB:
        warnings.append(
-            f"Uploaded file is {size_mb:.1f} MB — demo capped at "
+            f"Imported file is {size_mb:.1f} MB — demo capped at "
            f"{DEMO_FILE_CAP_MB} MB. The paid product has no size limit."
        )
        return sample_df.copy(), warnings
--- a/src/gui/components/_legacy.py
+++ b/src/gui/components/_legacy.py
@@ -347,7 +347,7 @@ body, .stApp {
    border-radius: var(--dt-r-sm) !important;
 }
 /* Hide Streamlit's built-in compact file-chip row once files exist —
-   the home page renders its own canonical "Uploaded files" list with
+   the home page renders its own canonical "Imported files" list with
   a Remove button beneath the uploader, so the chip row is redundant
   and visually doubles up on filenames. The dropzone's borderless
   ``+`` button is left in place as the "add more files" affordance.
@@ -459,6 +459,56 @@ div[data-testid="stContainer"][data-border="true"] {
 """


+# Streamlit ships the file_uploader's dropzone button with hard-coded
+# "Upload" text (it's a text node baked into the React component, not
+# a Streamlit i18n string we can override from Python). Our product
+# positioning is local-first, so the word "Upload" is misleading. This
+# script walks the dropzone buttons after first paint and rewrites the
+# label to "Import" — and re-runs on Streamlit's component-rerender
+# DOM mutations so the swap survives navigation and reruns.
+_RENAME_UPLOAD_BUTTON_JS = """
+<script>
+  (function () {
+    function swap(doc) {
+      var dropzones = doc.querySelectorAll('[data-testid="stFileUploaderDropzone"]');
+      dropzones.forEach(function (dz) {
+        var btn = dz.querySelector('button');
+        if (!btn) return;
+        // The label is a text node directly inside the outer label span;
+        // walk all text nodes and replace any exact "Upload".
+        var walker = doc.createTreeWalker(btn, NodeFilter.SHOW_TEXT, null, false);
+        var node;
+        while ((node = walker.nextNode())) {
+          if (node.nodeValue && node.nodeValue.trim() === 'Upload') {
+            node.nodeValue = node.nodeValue.replace('Upload', 'Import');
+          }
+        }
+      });
+    }
+    try {
+      var doc = window.parent.document;
+      swap(doc);
+      // Streamlit re-mounts dropzone subtrees on file changes / page
+      // switches — observe the parent doc and re-apply the swap when
+      // new ``stFileUploaderDropzone`` nodes appear. Throttled via
+      // requestAnimationFrame so a burst of mutations is one swap.
+      var raf = 0;
+      var obs = new (doc.defaultView || window).MutationObserver(function () {
+        if (raf) return;
+        raf = (doc.defaultView || window).requestAnimationFrame(function () {
+          raf = 0;
+          swap(doc);
+        });
+      });
+      obs.observe(doc.body, { childList: true, subtree: true });
+    } catch (e) {
+      swap(document);
+    }
+  })();
+</script>
+"""
+
+
 def hide_streamlit_chrome(*, gate_license: bool = True) -> None:
    """Inject CSS to hide Streamlit's default header, menu, and footer.

@@ -477,6 +527,10 @@ def hide_streamlit_chrome(*, gate_license: bool = True) -> None:
    """
    st.markdown(_HIDE_CHROME_CSS, unsafe_allow_html=True)
    st.markdown(_DESIGN_TOKENS_CSS, unsafe_allow_html=True)
+    # ``st.markdown`` doesn't execute embedded scripts; ship the
+    # Upload→Import rewriter through an iframe component the same way
+    # the sticky footer mounts on ``<body>``.
+    st.iframe(_RENAME_UPLOAD_BUTTON_JS, height=1)
    # Stamp a session-start record into the audit log the first time
    # any page renders. Idempotent — subsequent calls are no-ops.
    # Wrapped because a broken audit log MUST NOT take the GUI down.
--- a/src/gui/pages/1_Deduplicator.py
+++ b/src/gui/pages/1_Deduplicator.py
@@ -69,7 +69,7 @@ st.caption(t("tools.01_deduplicator.page_caption"))
 # ---------------------------------------------------------------------------

 uploaded = pickup_or_upload(
-    label="Upload CSV or Excel file",
+    label="Import CSV or Excel file",
    key="dedup_file_upload",
    types=["csv", "tsv", "xlsx", "xls"],
    help="Supports CSV, TSV, and Excel files. Encoding and delimiters are auto-detected.",
@@ -399,7 +399,7 @@ if uploaded is not None:

 else:
    # No file uploaded — show placeholder
-    st.info("Upload a file to get started.")
+    st.info("Import a file to get started.")


 # ---------------------------------------------------------------------------
--- a/src/gui/pages/2_Text_Cleaner.py
+++ b/src/gui/pages/2_Text_Cleaner.py
@@ -53,13 +53,13 @@ st.caption(t("tools.02_text_cleaner.page_caption"))
 # ---------------------------------------------------------------------------

 uploaded = pickup_or_upload(
-    label="Upload CSV or Excel file",
+    label="Import CSV or Excel file",
    key="textclean_file_upload",
    types=["csv", "tsv", "xlsx", "xls"],
 )

 if uploaded is None:
-    st.info("Upload a CSV, TSV, or Excel file to begin.")
+    st.info("Import a CSV, TSV, or Excel file to begin.")
    st.stop()


--- a/src/gui/pages/3_Format_Standardizer.py
+++ b/src/gui/pages/3_Format_Standardizer.py
@@ -52,13 +52,13 @@ st.caption(t("tools.03_format_standardizer.page_caption"))
 # ---------------------------------------------------------------------------

 uploaded = pickup_or_upload(
-    label="Upload CSV or Excel file",
+    label="Import CSV or Excel file",
    key="fmtstd_file_upload",
    types=["csv", "tsv", "xlsx", "xls"],
 )

 if uploaded is None:
-    st.info("Upload a CSV, TSV, or Excel file to begin.")
+    st.info("Import a CSV, TSV, or Excel file to begin.")
    st.stop()


--- a/src/gui/pages/4_Missing_Values.py
+++ b/src/gui/pages/4_Missing_Values.py
@@ -53,13 +53,13 @@ st.caption(t("tools.04_missing_handler.page_caption"))
 # ---------------------------------------------------------------------------

 uploaded = pickup_or_upload(
-    label="Upload CSV or Excel file",
+    label="Import CSV or Excel file",
    key="missing_file_upload",
    types=["csv", "tsv", "xlsx", "xls"],
 )

 if uploaded is None:
-    st.info("Upload a CSV, TSV, or Excel file to begin.")
+    st.info("Import a CSV, TSV, or Excel file to begin.")
    st.stop()


--- a/src/gui/pages/5_Column_Mapper.py
+++ b/src/gui/pages/5_Column_Mapper.py
@@ -54,13 +54,13 @@ st.caption(t("tools.05_column_mapper.page_caption"))
 # ---------------------------------------------------------------------------

 uploaded = pickup_or_upload(
-    label="Upload CSV or Excel file",
+    label="Import CSV or Excel file",
    key="colmap_file_upload",
    types=["csv", "tsv", "xlsx", "xls"],
 )

 if uploaded is None:
-    st.info("Upload a CSV, TSV, or Excel file to begin.")
+    st.info("Import a CSV, TSV, or Excel file to begin.")
    st.stop()


@@ -122,12 +122,12 @@ with st.expander("Options", expanded=not _has_result):
        "How would you like to define the target schema?",
        [
            "Build interactively (start from current columns)",
-            "Upload schema JSON",
+            "Import schema JSON",
            "Skip (rename / coerce only — no schema)",
        ],
        index=0,
        help=(
-            "An interactive build is fastest for one-off cleanup. Upload a JSON "
+            "An interactive build is fastest for one-off cleanup. Import a JSON "
            "when you have a fixed contract (a CRM import format, db schema). "
            "Skip when you only want to rename or coerce specific columns."
        ),
@@ -135,7 +135,7 @@ with st.expander("Options", expanded=not _has_result):

    schema: TargetSchema | None = None

-    if schema_mode.startswith("Upload"):
+    if schema_mode.startswith("Import"):
        schema_file = st.file_uploader(
            "Schema JSON",
            type=["json"],
--- a/src/gui/pages/6_Outlier_Detector.py
+++ b/src/gui/pages/6_Outlier_Detector.py
@@ -57,9 +57,9 @@ st.divider()
 # ---------------------------------------------------------------------------

 uploaded = st.file_uploader(
-    "Upload CSV or Excel file",
+    "Import CSV or Excel file",
    type=["csv", "tsv", "xlsx", "xls"],
-    help="Upload a file to preview. Processing is not yet available.",
+    help="Import a file to preview. Processing is not yet available.",
    key="outlier_file_upload",
 )

--- a/src/gui/pages/7_Multi_File_Merger.py
+++ b/src/gui/pages/7_Multi_File_Merger.py
@@ -42,7 +42,7 @@ st.info("This tool is under development.")

 st.markdown("""
 **Features:**
- Upload multiple CSV/Excel files at once
+- Import multiple CSV/Excel files at once
 - Automatic schema alignment (matching columns by name)
 - Append mode: stack files vertically (union)
 - Join mode: merge files on shared key columns
@@ -57,10 +57,10 @@ st.divider()
 # ---------------------------------------------------------------------------

 uploaded_files = st.file_uploader(
-    "Upload CSV or Excel files",
+    "Import CSV or Excel files",
    type=["csv", "tsv", "xlsx", "xls"],
    accept_multiple_files=True,
-    help="Upload multiple files to preview. Processing is not yet available.",
+    help="Import multiple files to preview. Processing is not yet available.",
    key="merger_file_upload",
 )

--- a/src/gui/pages/8_Validator_Reporter.py
+++ b/src/gui/pages/8_Validator_Reporter.py
@@ -57,9 +57,9 @@ st.divider()
 # ---------------------------------------------------------------------------

 uploaded = st.file_uploader(
-    "Upload CSV or Excel file",
+    "Import CSV or Excel file",
    type=["csv", "tsv", "xlsx", "xls"],
-    help="Upload a file to preview. Processing is not yet available.",
+    help="Import a file to preview. Processing is not yet available.",
    key="validator_file_upload",
 )

--- a/src/gui/pages/9_Pipeline_Runner.py
+++ b/src/gui/pages/9_Pipeline_Runner.py
@@ -55,13 +55,13 @@ st.caption(t("tools.09_pipeline_runner.page_caption"))
 # ---------------------------------------------------------------------------

 uploaded = pickup_or_upload(
-    label="Upload CSV or Excel file",
+    label="Import CSV or Excel file",
    key="pipeline_file_upload",
    types=["csv", "tsv", "xlsx", "xls"],
 )

 if uploaded is None:
-    st.info("Upload a CSV, TSV, or Excel file to begin.")
+    st.info("Import a CSV, TSV, or Excel file to begin.")
    st.stop()


@@ -119,7 +119,7 @@ with st.expander("Options", expanded=not _has_result):
        [
            "Use the recommended default (text-clean → format → missing → dedup)",
            "Build interactively",
-            "Upload a saved pipeline JSON",
+            "Import a saved pipeline JSON",
        ],
        index=0,
    )
@@ -143,7 +143,7 @@ with st.expander("Options", expanded=not _has_result):
            }
            for s in default.steps
        ])
-    elif mode.startswith("Upload"):
+    elif mode.startswith("Import"):
        pipeline_file = st.file_uploader(
            "Pipeline JSON", type=["json"], key="pipeline_upload",
        )
--- a/src/i18n/packs/en.json
+++ b/src/i18n/packs/en.json
@@ -15,23 +15,23 @@
    "coming_soon": "Coming Soon"
  },
  "upload": {
-    "heading": "📤 Upload one or more files to start",
-    "intro": "Optional: scan an uploaded file for data quality issues and see which tools can fix each one. Skip if you already know what you need.",
+    "heading": "📤 Import one or more files to start",
+    "intro": "Optional: scan an imported file for data quality issues and see which tools can fix each one. Skip if you already know what you need.",
    "limits": "**Up to 1.5 GB.** Formats: CSV, TSV, XLSX, XLS. Delimiters auto-detected: comma, tab, semicolon, pipe. Encodings auto-detected: UTF-8 (with/without BOM), UTF-16, cp1252, Latin-1/9, cp1250, ISO-8859-2, cp1251, KOI8-R, Mac Roman, Shift_JIS, GB18030, Big5, EUC-KR — and override on the Review page.",
-    "uploader_label": "Upload CSV or Excel",
+    "uploader_label": "Import CSV or Excel",
    "uploader_help": "Up to 1.5 GB. Comma / tab / semicolon / pipe delimiters all auto-detected. Encoding auto-detected with override on the Review page if needed.",
    "run_button": "Run analysis",
    "skip_button": "Skip",
    "scanning": "Scanning…",
    "skipped_notice": "Analysis skipped. Open any tool below to start working.",
-    "using_session_file": "Using **{name}** from the upload screen.",
+    "using_session_file": "Using **{name}** from the import screen.",
    "use_different_file": "Use a different file",
-    "switch_back": "Switch back to upload-screen file",
+    "switch_back": "Switch back to import-screen file",
    "pickup_caption": "Up to 1.5 GB. Delimiters auto-detected: comma, tab, semicolon, pipe. Encoding auto-detected (UTF-8 / UTF-16 / cp1252 / Latin-1 family / cp1250 / cp1251 / KOI8-R / Mac Roman / Shift_JIS / GB18030 / Big5 / EUC-KR), with override on the Review page.",
-    "intro_multi": "Drop files below. Each one is analyzed locally — no upload anywhere.",
-    "uploader_label_multi": "Upload CSV, TSV, or Excel files",
+    "intro_multi": "Drop files below. Each one is analyzed locally — nothing leaves this computer.",
+    "uploader_label_multi": "Import CSV, TSV, or Excel files",
    "clear_results": "Clear results",
-    "empty_state": "Upload one or more files to begin. Your data never leaves this computer."
+    "empty_state": "Import one or more files to begin. Your data never leaves this computer."
  },
  "findings": {
    "header": "Detected issues",
@@ -44,7 +44,7 @@
  },
  "gate": {
    "warning": "**{name}** must pass the CSV-normalization gate before you can use this tool. Open the Review page to apply the fixes our analyzer recommends.",
-    "default_name": "the uploaded file",
+    "default_name": "the imported file",
    "open_review": "Go to Review & Normalize"
  },
  "quit": {
--- a/src/i18n/packs/es.json
+++ b/src/i18n/packs/es.json
@@ -15,23 +15,23 @@
    "coming_soon": "Próximamente"
  },
  "upload": {
-    "heading": "📤 Sube uno o más archivos para empezar",
+    "heading": "📤 Importa uno o más archivos para empezar",
    "intro": "Opcional: analiza un archivo para detectar problemas de calidad de datos y ver qué herramientas pueden corregir cada uno. Sáltalo si ya sabes lo que necesitas.",
    "limits": "**Hasta 1,5 GB.** Formatos: CSV, TSV, XLSX, XLS. Delimitadores detectados automáticamente: coma, tabulador, punto y coma, barra vertical. Codificaciones detectadas automáticamente: UTF-8 (con/sin BOM), UTF-16, cp1252, Latin-1/9, cp1250, ISO-8859-2, cp1251, KOI8-R, Mac Roman, Shift_JIS, GB18030, Big5, EUC-KR — y se pueden sustituir desde la página Revisar.",
-    "uploader_label": "Sube un archivo CSV o Excel",
+    "uploader_label": "Importa un archivo CSV o Excel",
    "uploader_help": "Hasta 1,5 GB. Delimitadores coma / tabulador / punto y coma / barra vertical detectados automáticamente. Codificación detectada automáticamente, con opción de sustituirla en la página Revisar.",
    "run_button": "Ejecutar análisis",
    "skip_button": "Omitir",
    "scanning": "Analizando…",
    "skipped_notice": "Análisis omitido. Abre cualquier herramienta de abajo para empezar a trabajar.",
-    "using_session_file": "Usando **{name}** de la pantalla de carga.",
+    "using_session_file": "Usando **{name}** de la pantalla de importación.",
    "use_different_file": "Usar otro archivo",
-    "switch_back": "Volver al archivo de la pantalla de carga",
+    "switch_back": "Volver al archivo de la pantalla de importación",
    "pickup_caption": "Hasta 1,5 GB. Delimitadores detectados automáticamente: coma, tabulador, punto y coma, barra vertical. Codificación detectada automáticamente (UTF-8 / UTF-16 / cp1252 / familia Latin-1 / cp1250 / cp1251 / KOI8-R / Mac Roman / Shift_JIS / GB18030 / Big5 / EUC-KR), con opción de sustituirla en la página Revisar.",
-    "intro_multi": "Suelta archivos abajo. Cada uno se analiza localmente — no se sube a ningún lado.",
-    "uploader_label_multi": "Sube archivos CSV, TSV o Excel",
+    "intro_multi": "Suelta archivos abajo. Cada uno se analiza localmente — nada sale de este equipo.",
+    "uploader_label_multi": "Importa archivos CSV, TSV o Excel",
    "clear_results": "Borrar resultados",
-    "empty_state": "Sube uno o más archivos para empezar. Tus datos nunca salen de este equipo."
+    "empty_state": "Importa uno o más archivos para empezar. Tus datos nunca salen de este equipo."
  },
  "findings": {
    "header": "Problemas detectados",
@@ -44,7 +44,7 @@
  },
  "gate": {
    "warning": "**{name}** debe pasar la verificación de normalización CSV antes de poder usar esta herramienta. Abre la página Revisar para aplicar las correcciones recomendadas por el analizador.",
-    "default_name": "el archivo cargado",
+    "default_name": "el archivo importado",
    "open_review": "Ir a Revisar y Normalizar"
  },
  "quit": {