giteadmin/datatools-dev
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(text-cleaner): collapse options + auto-scroll to Results on run

Browse Source 
After clicking Clean Text the user was left at the bottom of the
script with the Options block still expanded and no viewport movement
— they had to scroll to find the Results.

- Wrap the whole Options block in an outer ``st.expander("Options",
  expanded=not _has_result)``. After the Clean Text rerun, both
  Preview AND Options collapse, leaving the primary action button +
  Results as the only prominent elements above the fold. The inner
  Advanced-options expander is preserved as a nested expander
  (supported in Streamlit 1.36+; this repo pins 1.35+).
- Add a 1px anchor div ``#textclean-results-anchor`` immediately
  before the Results subheader.
- On Clean Text click, set a one-shot ``_textclean_scroll_to_results``
  flag in session state; on the next render, pop the flag and inject
  a tiny ``st.components.v1.html`` iframe whose ``<script>`` calls
  ``scrollIntoView`` on the parent document's anchor. One-shot so
  re-renders triggered by other widgets (Show-hidden toggle, etc.)
  don't jerk the viewport back to the top of Results.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Michael
2026-05-16 20:50:43 +00:00
parent ca14ce2952
commit 0a61d52200
1 changed files with 121 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

198
src/gui/pages/2_Text_Cleaner.py
View File

@@ -123,82 +123,86 @@ st.divider()
# ---------------------------------------------------------------------------
# Options
# ---------------------------------------------------------------------------
#
# Wrapped in an outer expander whose default state mirrors the preview
# expander above: open before a result exists, folded once the user has
# clicked Clean Text. Together they push the Results section to the top
# of the visible area after a run.
st.subheader("Options")
preset_label = st.radio(
"Preset",
["excel-hygiene (recommended)", "minimal", "paranoid"],
index=0,
horizontal=True,
help=(
"excel-hygiene: trim, collapse whitespace, fold smart quotes, strip "
"invisible chars, normalize line endings, NFC. "
"minimal: only trim and collapse. "
"paranoid: everything including NFKC compat fold (lossy)."
),
)
preset_key = preset_label.split(" ", 1)[0]
options = CleanOptions.from_preset(preset_key)
with st.expander("Advanced options"):
col_a, col_b = st.columns(2)
with col_a:
options.trim = st.checkbox("Trim leading/trailing whitespace", value=options.trim)
options.collapse_whitespace = st.checkbox(
"Collapse internal whitespace", value=options.collapse_whitespace,
)
options.normalize_line_endings = st.checkbox(
"Normalize line endings (\\r\\n → \\n)", value=options.normalize_line_endings,
)
options.strip_control = st.checkbox(
"Strip control characters", value=options.strip_control,
)
options.strip_bom = st.checkbox("Strip BOM", value=options.strip_bom)
with col_b:
options.fold_smart_chars = st.checkbox(
"Fold smart characters (curly quotes, em-dash, NBSP)",
value=options.fold_smart_chars,
)
options.strip_zero_width = st.checkbox(
"Strip zero-width / invisible characters", value=options.strip_zero_width,
)
options.nfc = st.checkbox("Unicode NFC normalization", value=options.nfc)
options.nfkc = st.checkbox(
"Unicode NFKC compat fold (lossy: ① → 1, fi → fi)",
value=options.nfkc,
)
st.markdown("**Scope**")
string_cols = [
c for c in df.columns
if pd.api.types.is_object_dtype(df[c]) or pd.api.types.is_string_dtype(df[c])
]
selected_cols = st.multiselect(
"Columns to clean (default: all string columns)",
options=list(df.columns),
default=string_cols,
)
skip_cols = st.multiselect(
"Columns to skip even if they look like text",
options=list(df.columns),
default=[],
)
options.columns = selected_cols if selected_cols else None
options.skip_columns = list(skip_cols)
st.markdown("**Case conversion**")
case_global = st.selectbox(
"Apply case conversion to selected columns",
["None", "UPPER", "lower", "Title", "Sentence"],
with st.expander("Options", expanded=not _has_result):
preset_label = st.radio(
"Preset",
["excel-hygiene (recommended)", "minimal", "paranoid"],
index=0,
horizontal=True,
help=(
"excel-hygiene: trim, collapse whitespace, fold smart quotes, strip "
"invisible chars, normalize line endings, NFC. "
"minimal: only trim and collapse. "
"paranoid: everything including NFKC compat fold (lossy)."
),
)
case_map = {
"UPPER": "upper", "lower": "lower",
"Title": "title", "Sentence": "sentence",
}
if case_global != "None":
options.case = case_map[case_global] # type: ignore[assignment]
preset_key = preset_label.split(" ", 1)[0]
options = CleanOptions.from_preset(preset_key)
with st.expander("Advanced options"):
col_a, col_b = st.columns(2)
with col_a:
options.trim = st.checkbox("Trim leading/trailing whitespace", value=options.trim)
options.collapse_whitespace = st.checkbox(
"Collapse internal whitespace", value=options.collapse_whitespace,
)
options.normalize_line_endings = st.checkbox(
"Normalize line endings (\\r\\n → \\n)", value=options.normalize_line_endings,
)
options.strip_control = st.checkbox(
"Strip control characters", value=options.strip_control,
)
options.strip_bom = st.checkbox("Strip BOM", value=options.strip_bom)
with col_b:
options.fold_smart_chars = st.checkbox(
"Fold smart characters (curly quotes, em-dash, NBSP)",
value=options.fold_smart_chars,
)
options.strip_zero_width = st.checkbox(
"Strip zero-width / invisible characters", value=options.strip_zero_width,
)
options.nfc = st.checkbox("Unicode NFC normalization", value=options.nfc)
options.nfkc = st.checkbox(
"Unicode NFKC compat fold (lossy: ① → 1, fi → fi)",
value=options.nfkc,
)
st.markdown("**Scope**")
string_cols = [
c for c in df.columns
if pd.api.types.is_object_dtype(df[c]) or pd.api.types.is_string_dtype(df[c])
]
selected_cols = st.multiselect(
"Columns to clean (default: all string columns)",
options=list(df.columns),
default=string_cols,
)
skip_cols = st.multiselect(
"Columns to skip even if they look like text",
options=list(df.columns),
default=[],
)
options.columns = selected_cols if selected_cols else None
options.skip_columns = list(skip_cols)
st.markdown("**Case conversion**")
case_global = st.selectbox(
"Apply case conversion to selected columns",
["None", "UPPER", "lower", "Title", "Sentence"],
index=0,
)
case_map = {
"UPPER": "upper", "lower": "lower",
"Title": "title", "Sentence": "sentence",
}
if case_global != "None":
options.case = case_map[case_global] # type: ignore[assignment]
# ---------------------------------------------------------------------------
# Run
@@ -215,10 +219,13 @@ if st.button("Clean Text", type="primary", use_container_width=True):
st.stop()
st.session_state["textclean_result"] = result
st.session_state["textclean_input_name"] = uploaded.name
# Force a second rerun so the preview-section expander above sees
# the new result on its NEXT script pass and collapses itself.
# Without this the preview stays expanded until the user touches
# any other widget.
# One-shot flag picked up on the next pass to scroll the parent
# document to the Results anchor (see scroll snippet below).
st.session_state["_textclean_scroll_to_results"] = True
# Force a second rerun so the preview and options expanders see
# the new result on the NEXT script pass and collapse themselves.
# Without this they stay expanded until the user touches any
# other widget.
st.rerun()
result = st.session_state.get("textclean_result")
@@ -229,6 +236,16 @@ if result is None:
# Results
# ---------------------------------------------------------------------------
# Anchor target for the auto-scroll snippet at the end of this block.
# A bare ``<div id="...">`` survives Streamlit's HTML sanitizer (only
# ``<script>`` is stripped), and a 1px-tall div doesn't visually shift
# anything. Placed before the subheader so the scrolled-to viewport
# starts a few pixels above the section heading rather than below it.
st.markdown(
'<div id="textclean-results-anchor" style="height:1px"></div>',
unsafe_allow_html=True,
)
st.subheader("Results")
pct = (result.cells_changed / result.cells_total * 100.0) if result.cells_total else 0.0
@@ -344,3 +361,30 @@ with dl_c:
st.divider()
st.caption("Runs locally. Your data never leaves this computer. | DataTools v3.0")
# ---------------------------------------------------------------------------
# Post-run auto-scroll
# ---------------------------------------------------------------------------
#
# When the user clicks Clean Text, the preview + options collapse but
# Streamlit by itself doesn't scroll — the Results section is at the
# bottom of a tall script so the user has to find it. Inject a tiny
# component-html iframe that calls ``scrollIntoView`` on the parent's
# Results anchor. Streamlit's main page is same-origin with component
# iframes so ``window.parent.document`` access is allowed.
#
# The flag is one-shot (``pop`` removes it) so re-renders triggered by
# unrelated widgets in the Results section (e.g., the Show-hidden
# toggle) don't yank the viewport back to the top of Results.
if st.session_state.pop("_textclean_scroll_to_results", False):
from streamlit.components.v1 import html as _components_html
_components_html(
"""
<script>
const doc = window.parent.document;
const target = doc.getElementById('textclean-results-anchor');
if (target) target.scrollIntoView({behavior: 'smooth', block: 'start'});
</script>
""",
height=0,
)