dataframe-toolkit 0.15.0__tar.gz → 0.15.1__tar.gz

{dataframe_toolkit-0.15.0 → dataframe_toolkit-0.15.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: dataframe-toolkit
-Version: 0.15.0
+Version: 0.15.1
 Summary: A command-line toolkit for DataFrame analysis and manipulation
 Keywords: dataframe,statistics,data analysis,CLI,TSV,pandas
 Author: Gunnar Pálsson

{dataframe_toolkit-0.15.0 → dataframe_toolkit-0.15.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dataframe-toolkit"
-version = "0.15.0"
+version = "0.15.1"
 description = "A command-line toolkit for DataFrame analysis and manipulation"
 readme = "README.md"
 keywords = [

{dataframe_toolkit-0.15.0 → dataframe_toolkit-0.15.1}/pyproject.toml.orig

@@ -1,6 +1,6 @@
 [project]
 name = "dataframe-toolkit"
-version = "0.15.0"
+version = "0.15.1"
 description = "A command-line toolkit for DataFrame analysis and manipulation"
 readme = "README.md"
 authors = [

{dataframe_toolkit-0.15.0 → dataframe_toolkit-0.15.1}/src/dftk/commands/merge_cmd.py

@@ -29,6 +29,7 @@ import uuid
 import pandas as pd
 
 from dftk.commands.base import BaseCommand
+from dftk.common import docformats
 from dftk.common.io import check_cols, io
 
 logger = logging.getLogger(__name__)
@@ -113,6 +114,24 @@ def _add_cross_col(
     args.drop = drop
 
 
+def _carry_json_columns(
+    merged: pd.DataFrame,
+    left: pd.DataFrame,
+    right: pd.DataFrame,
+    suffixes: tuple[str, str],
+) -> None:
+    """Mark the JSON-text columns of both inputs in *merged* (see docformats)."""
+    names = []
+    for side, other, suffix in ((left, right, suffixes[0]), (right, left, suffixes[1])):
+        for col in docformats.json_columns(side):
+            name = col
+            if col in other.columns and f"{col}{suffix}" in merged.columns:
+                name = f"{col}{suffix}"
+            if name in merged.columns and name not in names:
+                names.append(name)
+    docformats.mark_json_columns(merged, names)
+
+
 def _gap_sides(args: argparse.Namespace) -> tuple[bool, bool]:
     """Return (left, right): which side's columns can get missing values.
 
@@ -227,6 +246,7 @@ def _do_merge(
     if "_merge" in df_merged.columns:
         df_merged = df_merged.drop(columns=["_merge"])
 
+    _carry_json_columns(df_merged, df_left, df_right, suffixes)
     return df_merged
 
 

{dataframe_toolkit-0.15.0 → dataframe_toolkit-0.15.1}/src/dftk/common/docformats.py

@@ -66,28 +66,35 @@ def _is_nested(value) -> bool:
 
 
 def _dumps(value) -> str:
-    return json.dumps(value, default=_plain, ensure_ascii=False, separators=(",", ":"))
+    text = json.dumps(value, default=_plain, ensure_ascii=False, separators=(",", ":"))
+    if "NaN" in text or "Infinity" in text:
+        # NaN and Infinity aren't JSON: write them as null
+        parsed = json.loads(text, parse_constant=lambda _: None)
+        text = json.dumps(parsed, ensure_ascii=False, separators=(",", ":"))
+    return text
 
 
 def nested_as_text(df: pd.DataFrame) -> pd.DataFrame:
     """Return *df* with nested values and JSON-column text as one-line text."""
     jcols = set(json_columns(df))
     out = None
-    for col in df.columns:
-        dtype = df[col].dtype
+    # By position: column names may repeat
+    for i, col in enumerate(df.columns):
+        series = df.iloc[:, i]
+        dtype = series.dtype
         if not (
             pd.api.types.is_object_dtype(dtype) or pd.api.types.is_string_dtype(dtype)
         ):
             continue
         if col in jcols:
-            new = df[col].map(_json_text_cell)
-        elif df[col].map(_is_nested).any():
-            new = df[col].map(lambda v: _dumps(v) if _is_nested(v) else v)
+            new = series.map(_json_text_cell)
+        elif series.map(_is_nested).any():
+            new = series.map(lambda v: _dumps(v) if _is_nested(v) else v)
         else:
             continue
         if out is None:
             out = df.copy()
-        out[col] = new
+        out.isetitem(i, new)
     return df if out is None else out
 
 
@@ -131,6 +138,12 @@ def write_json(df: pd.DataFrame, dest, lines: bool, digits: int | None) -> None:
 
     A missing value is written as null; the key is kept.
     """
+    repeated = df.columns[df.columns.duplicated()].unique().tolist()
+    if repeated:
+        raise ValueError(
+            f"JSON output needs unique column names; repeated: {repeated} "
+            "(rename one with --move OLD:NEW)"
+        )
     jcols = set(json_columns(df))
     cols = list(df.columns)
     records = (
@@ -173,7 +186,7 @@ def _table(df: pd.DataFrame, float_format: str | None, escape):
         [escape(_cell_text(v, float_format)) for v in row]
         for row in df.itertuples(index=False, name=None)
     ]
-    numeric = [_is_numeric(df[c]) for c in df.columns]
+    numeric = [_is_numeric(df.iloc[:, i]) for i in range(df.shape[1])]
     return header, rows, numeric
 
 
@@ -206,6 +219,9 @@ _LATEX_SPECIAL = {
     "_": r"\_",
     "{": r"\{",
     "}": r"\}",
+    # A row starting with [ after \\ would be read as \\[length]
+    "[": "{[}",
+    "]": "{]}",
     "~": r"\textasciitilde{}",
     "^": r"\textasciicircum{}",
     # The default OT1 font prints these as an em dash and as inverted ! and ?