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

feat: add delimiter selector for CSV/TSV files in GUI

Browse Source 
Auto-detects delimiter on upload and shows a selectbox with comma, tab,
semicolon, and pipe options. Changing re-reads the file immediately.
Line terminators (Windows/Unix/Mac) already handled by universal newlines.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Michael
2026-04-29 00:30:50 +00:00
parent 24ae566ec4
commit 310bea08bf
1 changed files with 41 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
src/gui/app.py
View File

@@ -19,7 +19,7 @@ if str(_project_root) not in sys.path:
sys.path.insert(0, str(_project_root))
from src.core.dedup import deduplicate, build_default_strategies, DeduplicationResult
from src.core.io import read_file, list_sheets
from src.core.io import read_file, list_sheets, detect_encoding, detect_delimiter
from src.core.config import DeduplicationConfig
from src.gui.components import (
apply_review_decisions,
@@ -56,6 +56,7 @@ _DEFAULTS = {
"config": None,
"file_name": "",
"sheet_names": [],
"detected_delimiter": ",",
}
for key, default in _DEFAULTS.items():
if key not in st.session_state:
@@ -96,11 +97,14 @@ if uploaded is not None:
tmp.write(uploaded.getvalue())
tmp_path = Path(tmp.name)
# Check for Excel sheets
# Check for Excel sheets / detect delimiter
if suffix.lower() in (".xlsx", ".xls"):
st.session_state["sheet_names"] = list_sheets(tmp_path)
st.session_state["detected_delimiter"] = ","
else:
st.session_state["sheet_names"] = []
enc = detect_encoding(tmp_path)
st.session_state["detected_delimiter"] = detect_delimiter(tmp_path, enc)
df = read_file(tmp_path)
if not isinstance(df, pd.DataFrame):
@@ -139,6 +143,41 @@ if uploaded is not None:
st.session_state["review_decisions"] = {}
tmp_path.unlink(missing_ok=True)
# Delimiter selector for CSV/TSV files
is_csv = Path(uploaded.name).suffix.lower() not in (".xlsx", ".xls")
if is_csv:
_DELIMITERS = {
"Comma (,)": ",",
"Tab (\\t)": "\t",
"Semicolon (;)": ";",
"Pipe (|)": "|",
}
_DELIM_LABELS = list(_DELIMITERS.keys())
_DELIM_VALUES = list(_DELIMITERS.values())
detected = st.session_state.get("detected_delimiter", ",")
default_idx = _DELIM_VALUES.index(detected) if detected in _DELIM_VALUES else 0
chosen_label = st.selectbox(
"Delimiter",
_DELIM_LABELS,
index=default_idx,
help="Auto-detected on upload. Change if the preview looks wrong.",
)
chosen_delim = _DELIMITERS[chosen_label]
if chosen_delim != st.session_state.get("_current_delimiter"):
st.session_state["_current_delimiter"] = chosen_delim
import tempfile
suffix = Path(uploaded.name).suffix
with tempfile.NamedTemporaryFile(delete=False, suffix=suffix) as tmp:
tmp.write(uploaded.getvalue())
tmp_path = Path(tmp.name)
df = read_file(tmp_path, delimiter=chosen_delim)
if not isinstance(df, pd.DataFrame):
df = pd.concat(list(df), ignore_index=True)
st.session_state["df"] = df
st.session_state["result"] = None
st.session_state["review_decisions"] = {}
tmp_path.unlink(missing_ok=True)
# Preview
st.subheader(f"Preview: {uploaded.name}")
st.caption(f"{len(df)} rows, {len(df.columns)} columns")