""" Module contains tools for processing files into DataFrames or other objects """ from collections import abc, defaultdict import csv import datetime from io import StringIO import itertools import re import sys from textwrap import fill from typing import ( Any, Dict, Iterable, Iterator, List, Optional, Sequence, Set, Type, cast, ) import warnings import numpy as np import pandas._libs.lib as lib import pandas._libs.ops as libops import pandas._libs.parsers as parsers from pandas._libs.parsers import STR_NA_VALUES from pandas._libs.tslibs import parsing from pandas._typing import FilePathOrBuffer, StorageOptions, Union from pandas.errors import ( AbstractMethodError, EmptyDataError, ParserError, ParserWarning, ) from pandas.util._decorators import Appender from pandas.core.dtypes.cast import astype_nansafe from pandas.core.dtypes.common import ( ensure_object, ensure_str, is_bool_dtype, is_categorical_dtype, is_dict_like, is_dtype_equal, is_extension_array_dtype, is_file_like, is_float, is_integer, is_integer_dtype, is_list_like, is_object_dtype, is_scalar, is_string_dtype, pandas_dtype, ) from pandas.core.dtypes.dtypes import CategoricalDtype from pandas.core.dtypes.missing import isna from pandas.core import algorithms, generic from pandas.core.arrays import Categorical from pandas.core.frame import DataFrame from pandas.core.indexes.api import ( Index, MultiIndex, RangeIndex, ensure_index_from_sequences, ) from pandas.core.series import Series from pandas.core.tools import datetimes as tools from pandas.io.common import IOHandles, get_handle, validate_header_arg from pandas.io.date_converters import generic_parser # BOM character (byte order mark) # This exists at the beginning of a file to indicate endianness # of a file (stream). Unfortunately, this marker screws up parsing, # so we need to remove it if we see it. _BOM = "\ufeff" _doc_read_csv_and_table = ( r""" {summary} Also supports optionally iterating or breaking of the file into chunks. Additional help can be found in the online docs for `IO Tools `_. Parameters ---------- filepath_or_buffer : str, path object or file-like object Any valid string path is acceptable. The string could be a URL. Valid URL schemes include http, ftp, s3, gs, and file. For file URLs, a host is expected. A local file could be: file://localhost/path/to/table.csv. If you want to pass in a path object, pandas accepts any ``os.PathLike``. By file-like object, we refer to objects with a ``read()`` method, such as a file handle (e.g. via builtin ``open`` function) or ``StringIO``. sep : str, default {_default_sep} Delimiter to use. If sep is None, the C engine cannot automatically detect the separator, but the Python parsing engine can, meaning the latter will be used and automatically detect the separator by Python's builtin sniffer tool, ``csv.Sniffer``. In addition, separators longer than 1 character and different from ``'\s+'`` will be interpreted as regular expressions and will also force the use of the Python parsing engine. Note that regex delimiters are prone to ignoring quoted data. Regex example: ``'\r\t'``. delimiter : str, default ``None`` Alias for sep. header : int, list of int, default 'infer' Row number(s) to use as the column names, and the start of the data. Default behavior is to infer the column names: if no names are passed the behavior is identical to ``header=0`` and column names are inferred from the first line of the file, if column names are passed explicitly then the behavior is identical to ``header=None``. Explicitly pass ``header=0`` to be able to replace existing names. The header can be a list of integers that specify row locations for a multi-index on the columns e.g. [0,1,3]. Intervening rows that are not specified will be skipped (e.g. 2 in this example is skipped). Note that this parameter ignores commented lines and empty lines if ``skip_blank_lines=True``, so ``header=0`` denotes the first line of data rather than the first line of the file. names : array-like, optional List of column names to use. If the file contains a header row, then you should explicitly pass ``header=0`` to override the column names. Duplicates in this list are not allowed. index_col : int, str, sequence of int / str, or False, default ``None`` Column(s) to use as the row labels of the ``DataFrame``, either given as string name or column index. If a sequence of int / str is given, a MultiIndex is used. Note: ``index_col=False`` can be used to force pandas to *not* use the first column as the index, e.g. when you have a malformed file with delimiters at the end of each line. usecols : list-like or callable, optional Return a subset of the columns. If list-like, all elements must either be positional (i.e. integer indices into the document columns) or strings that correspond to column names provided either by the user in `names` or inferred from the document header row(s). For example, a valid list-like `usecols` parameter would be ``[0, 1, 2]`` or ``['foo', 'bar', 'baz']``. Element order is ignored, so ``usecols=[0, 1]`` is the same as ``[1, 0]``. To instantiate a DataFrame from ``data`` with element order preserved use ``pd.read_csv(data, usecols=['foo', 'bar'])[['foo', 'bar']]`` for columns in ``['foo', 'bar']`` order or ``pd.read_csv(data, usecols=['foo', 'bar'])[['bar', 'foo']]`` for ``['bar', 'foo']`` order. If callable, the callable function will be evaluated against the column names, returning names where the callable function evaluates to True. An example of a valid callable argument would be ``lambda x: x.upper() in ['AAA', 'BBB', 'DDD']``. Using this parameter results in much faster parsing time and lower memory usage. squeeze : bool, default False If the parsed data only contains one column then return a Series. prefix : str, optional Prefix to add to column numbers when no header, e.g. 'X' for X0, X1, ... mangle_dupe_cols : bool, default True Duplicate columns will be specified as 'X', 'X.1', ...'X.N', rather than 'X'...'X'. Passing in False will cause data to be overwritten if there are duplicate names in the columns. dtype : Type name or dict of column -> type, optional Data type for data or columns. E.g. {{'a': np.float64, 'b': np.int32, 'c': 'Int64'}} Use `str` or `object` together with suitable `na_values` settings to preserve and not interpret dtype. If converters are specified, they will be applied INSTEAD of dtype conversion. engine : {{'c', 'python'}}, optional Parser engine to use. The C engine is faster while the python engine is currently more feature-complete. converters : dict, optional Dict of functions for converting values in certain columns. Keys can either be integers or column labels. true_values : list, optional Values to consider as True. false_values : list, optional Values to consider as False. skipinitialspace : bool, default False Skip spaces after delimiter. skiprows : list-like, int or callable, optional Line numbers to skip (0-indexed) or number of lines to skip (int) at the start of the file. If callable, the callable function will be evaluated against the row indices, returning True if the row should be skipped and False otherwise. An example of a valid callable argument would be ``lambda x: x in [0, 2]``. skipfooter : int, default 0 Number of lines at bottom of file to skip (Unsupported with engine='c'). nrows : int, optional Number of rows of file to read. Useful for reading pieces of large files. na_values : scalar, str, list-like, or dict, optional Additional strings to recognize as NA/NaN. If dict passed, specific per-column NA values. By default the following values are interpreted as NaN: '""" + fill("', '".join(sorted(STR_NA_VALUES)), 70, subsequent_indent=" ") + """'. keep_default_na : bool, default True Whether or not to include the default NaN values when parsing the data. Depending on whether `na_values` is passed in, the behavior is as follows: * If `keep_default_na` is True, and `na_values` are specified, `na_values` is appended to the default NaN values used for parsing. * If `keep_default_na` is True, and `na_values` are not specified, only the default NaN values are used for parsing. * If `keep_default_na` is False, and `na_values` are specified, only the NaN values specified `na_values` are used for parsing. * If `keep_default_na` is False, and `na_values` are not specified, no strings will be parsed as NaN. Note that if `na_filter` is passed in as False, the `keep_default_na` and `na_values` parameters will be ignored. na_filter : bool, default True Detect missing value markers (empty strings and the value of na_values). In data without any NAs, passing na_filter=False can improve the performance of reading a large file. verbose : bool, default False Indicate number of NA values placed in non-numeric columns. skip_blank_lines : bool, default True If True, skip over blank lines rather than interpreting as NaN values. parse_dates : bool or list of int or names or list of lists or dict, \ default False The behavior is as follows: * boolean. If True -> try parsing the index. * list of int or names. e.g. If [1, 2, 3] -> try parsing columns 1, 2, 3 each as a separate date column. * list of lists. e.g. If [[1, 3]] -> combine columns 1 and 3 and parse as a single date column. * dict, e.g. {{'foo' : [1, 3]}} -> parse columns 1, 3 as date and call result 'foo' If a column or index cannot be represented as an array of datetimes, say because of an unparsable value or a mixture of timezones, the column or index will be returned unaltered as an object data type. For non-standard datetime parsing, use ``pd.to_datetime`` after ``pd.read_csv``. To parse an index or column with a mixture of timezones, specify ``date_parser`` to be a partially-applied :func:`pandas.to_datetime` with ``utc=True``. See :ref:`io.csv.mixed_timezones` for more. Note: A fast-path exists for iso8601-formatted dates. infer_datetime_format : bool, default False If True and `parse_dates` is enabled, pandas will attempt to infer the format of the datetime strings in the columns, and if it can be inferred, switch to a faster method of parsing them. In some cases this can increase the parsing speed by 5-10x. keep_date_col : bool, default False If True and `parse_dates` specifies combining multiple columns then keep the original columns. date_parser : function, optional Function to use for converting a sequence of string columns to an array of datetime instances. The default uses ``dateutil.parser.parser`` to do the conversion. Pandas will try to call `date_parser` in three different ways, advancing to the next if an exception occurs: 1) Pass one or more arrays (as defined by `parse_dates`) as arguments; 2) concatenate (row-wise) the string values from the columns defined by `parse_dates` into a single array and pass that; and 3) call `date_parser` once for each row using one or more strings (corresponding to the columns defined by `parse_dates`) as arguments. dayfirst : bool, default False DD/MM format dates, international and European format. cache_dates : bool, default True If True, use a cache of unique, converted dates to apply the datetime conversion. May produce significant speed-up when parsing duplicate date strings, especially ones with timezone offsets. .. versionadded:: 0.25.0 iterator : bool, default False Return TextFileReader object for iteration or getting chunks with ``get_chunk()``. .. versionchanged:: 1.2 ``TextFileReader`` is a context manager. chunksize : int, optional Return TextFileReader object for iteration. See the `IO Tools docs `_ for more information on ``iterator`` and ``chunksize``. .. versionchanged:: 1.2 ``TextFileReader`` is a context manager. compression : {{'infer', 'gzip', 'bz2', 'zip', 'xz', None}}, default 'infer' For on-the-fly decompression of on-disk data. If 'infer' and `filepath_or_buffer` is path-like, then detect compression from the following extensions: '.gz', '.bz2', '.zip', or '.xz' (otherwise no decompression). If using 'zip', the ZIP file must contain only one data file to be read in. Set to None for no decompression. thousands : str, optional Thousands separator. decimal : str, default '.' Character to recognize as decimal point (e.g. use ',' for European data). lineterminator : str (length 1), optional Character to break file into lines. Only valid with C parser. quotechar : str (length 1), optional The character used to denote the start and end of a quoted item. Quoted items can include the delimiter and it will be ignored. quoting : int or csv.QUOTE_* instance, default 0 Control field quoting behavior per ``csv.QUOTE_*`` constants. Use one of QUOTE_MINIMAL (0), QUOTE_ALL (1), QUOTE_NONNUMERIC (2) or QUOTE_NONE (3). doublequote : bool, default ``True`` When quotechar is specified and quoting is not ``QUOTE_NONE``, indicate whether or not to interpret two consecutive quotechar elements INSIDE a field as a single ``quotechar`` element. escapechar : str (length 1), optional One-character string used to escape other characters. comment : str, optional Indicates remainder of line should not be parsed. If found at the beginning of a line, the line will be ignored altogether. This parameter must be a single character. Like empty lines (as long as ``skip_blank_lines=True``), fully commented lines are ignored by the parameter `header` but not by `skiprows`. For example, if ``comment='#'``, parsing ``#empty\\na,b,c\\n1,2,3`` with ``header=0`` will result in 'a,b,c' being treated as the header. encoding : str, optional Encoding to use for UTF when reading/writing (ex. 'utf-8'). `List of Python standard encodings `_ . .. versionchanged:: 1.2 When ``encoding`` is ``None``, ``errors="replace"`` is passed to ``open()``. Otherwise, ``errors="strict"`` is passed to ``open()``. This behavior was previously only the case for ``engine="python"``. dialect : str or csv.Dialect, optional If provided, this parameter will override values (default or not) for the following parameters: `delimiter`, `doublequote`, `escapechar`, `skipinitialspace`, `quotechar`, and `quoting`. If it is necessary to override values, a ParserWarning will be issued. See csv.Dialect documentation for more details. error_bad_lines : bool, default True Lines with too many fields (e.g. a csv line with too many commas) will by default cause an exception to be raised, and no DataFrame will be returned. If False, then these "bad lines" will dropped from the DataFrame that is returned. warn_bad_lines : bool, default True If error_bad_lines is False, and warn_bad_lines is True, a warning for each "bad line" will be output. delim_whitespace : bool, default False Specifies whether or not whitespace (e.g. ``' '`` or ``'\t'``) will be used as the sep. Equivalent to setting ``sep='\\s+'``. If this option is set to True, nothing should be passed in for the ``delimiter`` parameter. low_memory : bool, default True Internally process the file in chunks, resulting in lower memory use while parsing, but possibly mixed type inference. To ensure no mixed types either set False, or specify the type with the `dtype` parameter. Note that the entire file is read into a single DataFrame regardless, use the `chunksize` or `iterator` parameter to return the data in chunks. (Only valid with C parser). memory_map : bool, default False If a filepath is provided for `filepath_or_buffer`, map the file object directly onto memory and access the data directly from there. Using this option can improve performance because there is no longer any I/O overhead. float_precision : str, optional Specifies which converter the C engine should use for floating-point values. The options are ``None`` or 'high' for the ordinary converter, 'legacy' for the original lower precision pandas converter, and 'round_trip' for the round-trip converter. .. versionchanged:: 1.2 {storage_options} .. versionadded:: 1.2 Returns ------- DataFrame or TextParser A comma-separated values (csv) file is returned as two-dimensional data structure with labeled axes. See Also -------- DataFrame.to_csv : Write DataFrame to a comma-separated values (csv) file. read_csv : Read a comma-separated values (csv) file into DataFrame. read_fwf : Read a table of fixed-width formatted lines into DataFrame. Examples -------- >>> pd.{func_name}('data.csv') # doctest: +SKIP """ ) def validate_integer(name, val, min_val=0): """ Checks whether the 'name' parameter for parsing is either an integer OR float that can SAFELY be cast to an integer without losing accuracy. Raises a ValueError if that is not the case. Parameters ---------- name : string Parameter name (used for error reporting) val : int or float The value to check min_val : int Minimum allowed value (val < min_val will result in a ValueError) """ msg = f"'{name:s}' must be an integer >={min_val:d}" if val is not None: if is_float(val): if int(val) != val: raise ValueError(msg) val = int(val) elif not (is_integer(val) and val >= min_val): raise ValueError(msg) return val def _validate_names(names): """ Raise ValueError if the `names` parameter contains duplicates or has an invalid data type. Parameters ---------- names : array-like or None An array containing a list of the names used for the output DataFrame. Raises ------ ValueError If names are not unique or are not ordered (e.g. set). """ if names is not None: if len(names) != len(set(names)): raise ValueError("Duplicate names are not allowed.") if not ( is_list_like(names, allow_sets=False) or isinstance(names, abc.KeysView) ): raise ValueError("Names should be an ordered collection.") def _read(filepath_or_buffer: FilePathOrBuffer, kwds): """Generic reader of line files.""" if kwds.get("date_parser", None) is not None: if isinstance(kwds["parse_dates"], bool): kwds["parse_dates"] = True # Extract some of the arguments (pass chunksize on). iterator = kwds.get("iterator", False) chunksize = validate_integer("chunksize", kwds.get("chunksize", None), 1) nrows = kwds.get("nrows", None) # Check for duplicates in names. _validate_names(kwds.get("names", None)) # Create the parser. parser = TextFileReader(filepath_or_buffer, **kwds) if chunksize or iterator: return parser with parser: return parser.read(nrows) _parser_defaults = { "delimiter": None, "escapechar": None, "quotechar": '"', "quoting": csv.QUOTE_MINIMAL, "doublequote": True, "skipinitialspace": False, "lineterminator": None, "header": "infer", "index_col": None, "names": None, "prefix": None, "skiprows": None, "skipfooter": 0, "nrows": None, "na_values": None, "keep_default_na": True, "true_values": None, "false_values": None, "converters": None, "dtype": None, "cache_dates": True, "thousands": None, "comment": None, "decimal": ".", # 'engine': 'c', "parse_dates": False, "keep_date_col": False, "dayfirst": False, "date_parser": None, "usecols": None, # 'iterator': False, "chunksize": None, "verbose": False, "encoding": None, "squeeze": False, "compression": None, "mangle_dupe_cols": True, "infer_datetime_format": False, "skip_blank_lines": True, } _c_parser_defaults = { "delim_whitespace": False, "na_filter": True, "low_memory": True, "memory_map": False, "error_bad_lines": True, "warn_bad_lines": True, "float_precision": None, } _fwf_defaults = {"colspecs": "infer", "infer_nrows": 100, "widths": None} _c_unsupported = {"skipfooter"} _python_unsupported = {"low_memory", "float_precision"} _deprecated_defaults: Dict[str, Any] = {} _deprecated_args: Set[str] = set() @Appender( _doc_read_csv_and_table.format( func_name="read_csv", summary="Read a comma-separated values (csv) file into DataFrame.", _default_sep="','", storage_options=generic._shared_docs["storage_options"], ) ) def read_csv( filepath_or_buffer: FilePathOrBuffer, sep=lib.no_default, delimiter=None, # Column and Index Locations and Names header="infer", names=None, index_col=None, usecols=None, squeeze=False, prefix=None, mangle_dupe_cols=True, # General Parsing Configuration dtype=None, engine=None, converters=None, true_values=None, false_values=None, skipinitialspace=False, skiprows=None, skipfooter=0, nrows=None, # NA and Missing Data Handling na_values=None, keep_default_na=True, na_filter=True, verbose=False, skip_blank_lines=True, # Datetime Handling parse_dates=False, infer_datetime_format=False, keep_date_col=False, date_parser=None, dayfirst=False, cache_dates=True, # Iteration iterator=False, chunksize=None, # Quoting, Compression, and File Format compression="infer", thousands=None, decimal: str = ".", lineterminator=None, quotechar='"', quoting=csv.QUOTE_MINIMAL, doublequote=True, escapechar=None, comment=None, encoding=None, dialect=None, # Error Handling error_bad_lines=True, warn_bad_lines=True, # Internal delim_whitespace=False, low_memory=_c_parser_defaults["low_memory"], memory_map=False, float_precision=None, storage_options: StorageOptions = None, ): kwds = locals() del kwds["filepath_or_buffer"] del kwds["sep"] kwds_defaults = _refine_defaults_read( dialect, delimiter, delim_whitespace, engine, sep, defaults={"delimiter": ","} ) kwds.update(kwds_defaults) return _read(filepath_or_buffer, kwds) @Appender( _doc_read_csv_and_table.format( func_name="read_table", summary="Read general delimited file into DataFrame.", _default_sep=r"'\\t' (tab-stop)", storage_options=generic._shared_docs["storage_options"], ) ) def read_table( filepath_or_buffer: FilePathOrBuffer, sep=lib.no_default, delimiter=None, # Column and Index Locations and Names header="infer", names=None, index_col=None, usecols=None, squeeze=False, prefix=None, mangle_dupe_cols=True, # General Parsing Configuration dtype=None, engine=None, converters=None, true_values=None, false_values=None, skipinitialspace=False, skiprows=None, skipfooter=0, nrows=None, # NA and Missing Data Handling na_values=None, keep_default_na=True, na_filter=True, verbose=False, skip_blank_lines=True, # Datetime Handling parse_dates=False, infer_datetime_format=False, keep_date_col=False, date_parser=None, dayfirst=False, cache_dates=True, # Iteration iterator=False, chunksize=None, # Quoting, Compression, and File Format compression="infer", thousands=None, decimal: str = ".", lineterminator=None, quotechar='"', quoting=csv.QUOTE_MINIMAL, doublequote=True, escapechar=None, comment=None, encoding=None, dialect=None, # Error Handling error_bad_lines=True, warn_bad_lines=True, # Internal delim_whitespace=False, low_memory=_c_parser_defaults["low_memory"], memory_map=False, float_precision=None, ): kwds = locals() del kwds["filepath_or_buffer"] del kwds["sep"] kwds_defaults = _refine_defaults_read( dialect, delimiter, delim_whitespace, engine, sep, defaults={"delimiter": "\t"} ) kwds.update(kwds_defaults) return _read(filepath_or_buffer, kwds) def read_fwf( filepath_or_buffer: FilePathOrBuffer, colspecs="infer", widths=None, infer_nrows=100, **kwds, ): r""" Read a table of fixed-width formatted lines into DataFrame. Also supports optionally iterating or breaking of the file into chunks. Additional help can be found in the `online docs for IO Tools `_. Parameters ---------- filepath_or_buffer : str, path object or file-like object Any valid string path is acceptable. The string could be a URL. Valid URL schemes include http, ftp, s3, and file. For file URLs, a host is expected. A local file could be: ``file://localhost/path/to/table.csv``. If you want to pass in a path object, pandas accepts any ``os.PathLike``. By file-like object, we refer to objects with a ``read()`` method, such as a file handle (e.g. via builtin ``open`` function) or ``StringIO``. colspecs : list of tuple (int, int) or 'infer'. optional A list of tuples giving the extents of the fixed-width fields of each line as half-open intervals (i.e., [from, to[ ). String value 'infer' can be used to instruct the parser to try detecting the column specifications from the first 100 rows of the data which are not being skipped via skiprows (default='infer'). widths : list of int, optional A list of field widths which can be used instead of 'colspecs' if the intervals are contiguous. infer_nrows : int, default 100 The number of rows to consider when letting the parser determine the `colspecs`. .. versionadded:: 0.24.0 **kwds : optional Optional keyword arguments can be passed to ``TextFileReader``. Returns ------- DataFrame or TextParser A comma-separated values (csv) file is returned as two-dimensional data structure with labeled axes. See Also -------- DataFrame.to_csv : Write DataFrame to a comma-separated values (csv) file. read_csv : Read a comma-separated values (csv) file into DataFrame. Examples -------- >>> pd.read_fwf('data.csv') # doctest: +SKIP """ # Check input arguments. if colspecs is None and widths is None: raise ValueError("Must specify either colspecs or widths") elif colspecs not in (None, "infer") and widths is not None: raise ValueError("You must specify only one of 'widths' and 'colspecs'") # Compute 'colspecs' from 'widths', if specified. if widths is not None: colspecs, col = [], 0 for w in widths: colspecs.append((col, col + w)) col += w kwds["colspecs"] = colspecs kwds["infer_nrows"] = infer_nrows kwds["engine"] = "python-fwf" return _read(filepath_or_buffer, kwds) class TextFileReader(abc.Iterator): """ Passed dialect overrides any of the related parser options """ def __init__(self, f, engine=None, **kwds): self.f = f if engine is not None: engine_specified = True else: engine = "python" engine_specified = False self.engine = engine self._engine_specified = kwds.get("engine_specified", engine_specified) _validate_skipfooter(kwds) dialect = _extract_dialect(kwds) if dialect is not None: kwds = _merge_with_dialect_properties(dialect, kwds) if kwds.get("header", "infer") == "infer": kwds["header"] = 0 if kwds.get("names") is None else None self.orig_options = kwds # miscellanea self._currow = 0 options = self._get_options_with_defaults(engine) options["storage_options"] = kwds.get("storage_options", None) self.chunksize = options.pop("chunksize", None) self.nrows = options.pop("nrows", None) self.squeeze = options.pop("squeeze", False) self._check_file_or_buffer(f, engine) self.options, self.engine = self._clean_options(options, engine) if "has_index_names" in kwds: self.options["has_index_names"] = kwds["has_index_names"] self._engine = self._make_engine(self.engine) def close(self): self._engine.close() def _get_options_with_defaults(self, engine): kwds = self.orig_options options = {} for argname, default in _parser_defaults.items(): value = kwds.get(argname, default) # see gh-12935 if argname == "mangle_dupe_cols" and not value: raise ValueError("Setting mangle_dupe_cols=False is not supported yet") else: options[argname] = value for argname, default in _c_parser_defaults.items(): if argname in kwds: value = kwds[argname] if engine != "c" and value != default: if "python" in engine and argname not in _python_unsupported: pass elif value == _deprecated_defaults.get(argname, default): pass else: raise ValueError( f"The {repr(argname)} option is not supported with the " f"{repr(engine)} engine" ) else: value = _deprecated_defaults.get(argname, default) options[argname] = value if engine == "python-fwf": # pandas\io\parsers.py:907: error: Incompatible types in assignment # (expression has type "object", variable has type "Union[int, str, # None]") [assignment] for argname, default in _fwf_defaults.items(): # type: ignore[assignment] options[argname] = kwds.get(argname, default) return options def _check_file_or_buffer(self, f, engine): # see gh-16530 if is_file_like(f) and engine != "c" and not hasattr(f, "__next__"): # The C engine doesn't need the file-like to have the "__next__" # attribute. However, the Python engine explicitly calls # "__next__(...)" when iterating through such an object, meaning it # needs to have that attribute raise ValueError( "The 'python' engine cannot iterate through this file buffer." ) def _clean_options(self, options, engine): result = options.copy() fallback_reason = None # C engine not supported yet if engine == "c": if options["skipfooter"] > 0: fallback_reason = "the 'c' engine does not support skipfooter" engine = "python" sep = options["delimiter"] delim_whitespace = options["delim_whitespace"] if sep is None and not delim_whitespace: if engine == "c": fallback_reason = ( "the 'c' engine does not support " "sep=None with delim_whitespace=False" ) engine = "python" elif sep is not None and len(sep) > 1: if engine == "c" and sep == r"\s+": result["delim_whitespace"] = True del result["delimiter"] elif engine not in ("python", "python-fwf"): # wait until regex engine integrated fallback_reason = ( "the 'c' engine does not support " "regex separators (separators > 1 char and " r"different from '\s+' are interpreted as regex)" ) engine = "python" elif delim_whitespace: if "python" in engine: result["delimiter"] = r"\s+" elif sep is not None: encodeable = True encoding = sys.getfilesystemencoding() or "utf-8" try: if len(sep.encode(encoding)) > 1: encodeable = False except UnicodeDecodeError: encodeable = False if not encodeable and engine not in ("python", "python-fwf"): fallback_reason = ( f"the separator encoded in {encoding} " "is > 1 char long, and the 'c' engine " "does not support such separators" ) engine = "python" quotechar = options["quotechar"] if quotechar is not None and isinstance(quotechar, (str, bytes)): if ( len(quotechar) == 1 and ord(quotechar) > 127 and engine not in ("python", "python-fwf") ): fallback_reason = ( "ord(quotechar) > 127, meaning the " "quotechar is larger than one byte, " "and the 'c' engine does not support such quotechars" ) engine = "python" if fallback_reason and self._engine_specified: raise ValueError(fallback_reason) if engine == "c": for arg in _c_unsupported: del result[arg] if "python" in engine: for arg in _python_unsupported: if fallback_reason and result[arg] != _c_parser_defaults[arg]: raise ValueError( "Falling back to the 'python' engine because " f"{fallback_reason}, but this causes {repr(arg)} to be " "ignored as it is not supported by the 'python' engine." ) del result[arg] if fallback_reason: warnings.warn( ( "Falling back to the 'python' engine because " f"{fallback_reason}; you can avoid this warning by specifying " "engine='python'." ), ParserWarning, stacklevel=5, ) index_col = options["index_col"] names = options["names"] converters = options["converters"] na_values = options["na_values"] skiprows = options["skiprows"] validate_header_arg(options["header"]) for arg in _deprecated_args: parser_default = _c_parser_defaults[arg] depr_default = _deprecated_defaults[arg] if result.get(arg, depr_default) != depr_default: msg = ( f"The {arg} argument has been deprecated and will be " "removed in a future version.\n\n" ) warnings.warn(msg, FutureWarning, stacklevel=2) else: result[arg] = parser_default if index_col is True: raise ValueError("The value of index_col couldn't be 'True'") if _is_index_col(index_col): if not isinstance(index_col, (list, tuple, np.ndarray)): index_col = [index_col] result["index_col"] = index_col names = list(names) if names is not None else names # type conversion-related if converters is not None: if not isinstance(converters, dict): raise TypeError( "Type converters must be a dict or subclass, " f"input was a {type(converters).__name__}" ) else: converters = {} # Converting values to NA keep_default_na = options["keep_default_na"] na_values, na_fvalues = _clean_na_values(na_values, keep_default_na) # handle skiprows; this is internally handled by the # c-engine, so only need for python parsers if engine != "c": if is_integer(skiprows): skiprows = list(range(skiprows)) if skiprows is None: skiprows = set() elif not callable(skiprows): skiprows = set(skiprows) # put stuff back result["names"] = names result["converters"] = converters result["na_values"] = na_values result["na_fvalues"] = na_fvalues result["skiprows"] = skiprows return result, engine def __next__(self): try: return self.get_chunk() except StopIteration: self.close() raise def _make_engine(self, engine="c"): mapping: Dict[str, Type[ParserBase]] = { "c": CParserWrapper, "python": PythonParser, "python-fwf": FixedWidthFieldParser, } if engine not in mapping: raise ValueError( f"Unknown engine: {engine} (valid options are {mapping.keys()})" ) # error: Too many arguments for "ParserBase" return mapping[engine](self.f, **self.options) # type: ignore[call-arg] def _failover_to_python(self): raise AbstractMethodError(self) def read(self, nrows=None): nrows = validate_integer("nrows", nrows) index, columns, col_dict = self._engine.read(nrows) if index is None: if col_dict: # Any column is actually fine: new_rows = len(next(iter(col_dict.values()))) index = RangeIndex(self._currow, self._currow + new_rows) else: new_rows = 0 else: new_rows = len(index) df = DataFrame(col_dict, columns=columns, index=index) self._currow += new_rows if self.squeeze and len(df.columns) == 1: return df[df.columns[0]].copy() return df def get_chunk(self, size=None): if size is None: size = self.chunksize if self.nrows is not None: if self._currow >= self.nrows: raise StopIteration size = min(size, self.nrows - self._currow) return self.read(nrows=size) def __enter__(self): return self def __exit__(self, exc_type, exc_value, traceback): self.close() def _is_index_col(col): return col is not None and col is not False def _is_potential_multi_index( columns, index_col: Optional[Union[bool, Sequence[int]]] = None ): """ Check whether or not the `columns` parameter could be converted into a MultiIndex. Parameters ---------- columns : array-like Object which may or may not be convertible into a MultiIndex index_col : None, bool or list, optional Column or columns to use as the (possibly hierarchical) index Returns ------- boolean : Whether or not columns could become a MultiIndex """ if index_col is None or isinstance(index_col, bool): index_col = [] return ( len(columns) and not isinstance(columns, MultiIndex) and all(isinstance(c, tuple) for c in columns if c not in list(index_col)) ) def _evaluate_usecols(usecols, names): """ Check whether or not the 'usecols' parameter is a callable. If so, enumerates the 'names' parameter and returns a set of indices for each entry in 'names' that evaluates to True. If not a callable, returns 'usecols'. """ if callable(usecols): return {i for i, name in enumerate(names) if usecols(name)} return usecols def _validate_usecols_names(usecols, names): """ Validates that all usecols are present in a given list of names. If not, raise a ValueError that shows what usecols are missing. Parameters ---------- usecols : iterable of usecols The columns to validate are present in names. names : iterable of names The column names to check against. Returns ------- usecols : iterable of usecols The `usecols` parameter if the validation succeeds. Raises ------ ValueError : Columns were missing. Error message will list them. """ missing = [c for c in usecols if c not in names] if len(missing) > 0: raise ValueError( f"Usecols do not match columns, columns expected but not found: {missing}" ) return usecols def _validate_skipfooter_arg(skipfooter): """ Validate the 'skipfooter' parameter. Checks whether 'skipfooter' is a non-negative integer. Raises a ValueError if that is not the case. Parameters ---------- skipfooter : non-negative integer The number of rows to skip at the end of the file. Returns ------- validated_skipfooter : non-negative integer The original input if the validation succeeds. Raises ------ ValueError : 'skipfooter' was not a non-negative integer. """ if not is_integer(skipfooter): raise ValueError("skipfooter must be an integer") if skipfooter < 0: raise ValueError("skipfooter cannot be negative") return skipfooter def _validate_usecols_arg(usecols): """ Validate the 'usecols' parameter. Checks whether or not the 'usecols' parameter contains all integers (column selection by index), strings (column by name) or is a callable. Raises a ValueError if that is not the case. Parameters ---------- usecols : list-like, callable, or None List of columns to use when parsing or a callable that can be used to filter a list of table columns. Returns ------- usecols_tuple : tuple A tuple of (verified_usecols, usecols_dtype). 'verified_usecols' is either a set if an array-like is passed in or 'usecols' if a callable or None is passed in. 'usecols_dtype` is the inferred dtype of 'usecols' if an array-like is passed in or None if a callable or None is passed in. """ msg = ( "'usecols' must either be list-like of all strings, all unicode, " "all integers or a callable." ) if usecols is not None: if callable(usecols): return usecols, None if not is_list_like(usecols): # see gh-20529 # # Ensure it is iterable container but not string. raise ValueError(msg) usecols_dtype = lib.infer_dtype(usecols, skipna=False) if usecols_dtype not in ("empty", "integer", "string"): raise ValueError(msg) usecols = set(usecols) return usecols, usecols_dtype return usecols, None def _validate_parse_dates_arg(parse_dates): """ Check whether or not the 'parse_dates' parameter is a non-boolean scalar. Raises a ValueError if that is the case. """ msg = ( "Only booleans, lists, and dictionaries are accepted " "for the 'parse_dates' parameter" ) if parse_dates is not None: if is_scalar(parse_dates): if not lib.is_bool(parse_dates): raise TypeError(msg) elif not isinstance(parse_dates, (list, dict)): raise TypeError(msg) return parse_dates class ParserBase: def __init__(self, kwds): self.names = kwds.get("names") self.orig_names: Optional[List] = None self.prefix = kwds.pop("prefix", None) self.index_col = kwds.get("index_col", None) self.unnamed_cols: Set = set() self.index_names: Optional[List] = None self.col_names = None self.parse_dates = _validate_parse_dates_arg(kwds.pop("parse_dates", False)) self.date_parser = kwds.pop("date_parser", None) self.dayfirst = kwds.pop("dayfirst", False) self.keep_date_col = kwds.pop("keep_date_col", False) self.na_values = kwds.get("na_values") self.na_fvalues = kwds.get("na_fvalues") self.na_filter = kwds.get("na_filter", False) self.keep_default_na = kwds.get("keep_default_na", True) self.true_values = kwds.get("true_values") self.false_values = kwds.get("false_values") self.mangle_dupe_cols = kwds.get("mangle_dupe_cols", True) self.infer_datetime_format = kwds.pop("infer_datetime_format", False) self.cache_dates = kwds.pop("cache_dates", True) self._date_conv = _make_date_converter( date_parser=self.date_parser, dayfirst=self.dayfirst, infer_datetime_format=self.infer_datetime_format, cache_dates=self.cache_dates, ) # validate header options for mi self.header = kwds.get("header") if isinstance(self.header, (list, tuple, np.ndarray)): if not all(map(is_integer, self.header)): raise ValueError("header must be integer or list of integers") if any(i < 0 for i in self.header): raise ValueError( "cannot specify multi-index header with negative integers" ) if kwds.get("usecols"): raise ValueError( "cannot specify usecols when specifying a multi-index header" ) if kwds.get("names"): raise ValueError( "cannot specify names when specifying a multi-index header" ) # validate index_col that only contains integers if self.index_col is not None: is_sequence = isinstance(self.index_col, (list, tuple, np.ndarray)) if not ( is_sequence and all(map(is_integer, self.index_col)) or is_integer(self.index_col) ): raise ValueError( "index_col must only contain row numbers " "when specifying a multi-index header" ) elif self.header is not None: # GH 27394 if self.prefix is not None: raise ValueError( "Argument prefix must be None if argument header is not None" ) # GH 16338 elif not is_integer(self.header): raise ValueError("header must be integer or list of integers") # GH 27779 elif self.header < 0: raise ValueError( "Passing negative integer to header is invalid. " "For no header, use header=None instead" ) self._name_processed = False self._first_chunk = True self.handles: Optional[IOHandles] = None def _open_handles(self, src: FilePathOrBuffer, kwds: Dict[str, Any]) -> None: """ Let the readers open IOHanldes after they are done with their potential raises. """ self.handles = get_handle( src, "r", encoding=kwds.get("encoding", None), compression=kwds.get("compression", None), memory_map=kwds.get("memory_map", False), storage_options=kwds.get("storage_options", None), ) def _validate_parse_dates_presence(self, columns: List[str]) -> None: """ Check if parse_dates are in columns. If user has provided names for parse_dates, check if those columns are available. Parameters ---------- columns : list List of names of the dataframe. Raises ------ ValueError If column to parse_date is not in dataframe. """ cols_needed: Iterable if is_dict_like(self.parse_dates): cols_needed = itertools.chain(*self.parse_dates.values()) elif is_list_like(self.parse_dates): # a column in parse_dates could be represented # ColReference = Union[int, str] # DateGroups = List[ColReference] # ParseDates = Union[DateGroups, List[DateGroups], # Dict[ColReference, DateGroups]] cols_needed = itertools.chain.from_iterable( col if is_list_like(col) else [col] for col in self.parse_dates ) else: cols_needed = [] # get only columns that are references using names (str), not by index missing_cols = ", ".join( sorted( { col for col in cols_needed if isinstance(col, str) and col not in columns } ) ) if missing_cols: raise ValueError( f"Missing column provided to 'parse_dates': '{missing_cols}'" ) def close(self): if self.handles is not None: self.handles.close() @property def _has_complex_date_col(self): return isinstance(self.parse_dates, dict) or ( isinstance(self.parse_dates, list) and len(self.parse_dates) > 0 and isinstance(self.parse_dates[0], list) ) def _should_parse_dates(self, i): if isinstance(self.parse_dates, bool): return self.parse_dates else: if self.index_names is not None: name = self.index_names[i] else: name = None j = self.index_col[i] if is_scalar(self.parse_dates): return (j == self.parse_dates) or ( name is not None and name == self.parse_dates ) else: return (j in self.parse_dates) or ( name is not None and name in self.parse_dates ) def _extract_multi_indexer_columns( self, header, index_names, col_names, passed_names=False ): """ extract and return the names, index_names, col_names header is a list-of-lists returned from the parsers """ if len(header) < 2: return header[0], index_names, col_names, passed_names # the names are the tuples of the header that are not the index cols # 0 is the name of the index, assuming index_col is a list of column # numbers ic = self.index_col if ic is None: ic = [] if not isinstance(ic, (list, tuple, np.ndarray)): ic = [ic] sic = set(ic) # clean the index_names index_names = header.pop(-1) index_names, names, index_col = _clean_index_names( index_names, self.index_col, self.unnamed_cols ) # extract the columns field_count = len(header[0]) def extract(r): return tuple(r[i] for i in range(field_count) if i not in sic) columns = list(zip(*(extract(r) for r in header))) names = ic + columns # If we find unnamed columns all in a single # level, then our header was too long. for n in range(len(columns[0])): if all(ensure_str(col[n]) in self.unnamed_cols for col in columns): header = ",".join(str(x) for x in self.header) raise ParserError( f"Passed header=[{header}] are too many rows " "for this multi_index of columns" ) # Clean the column names (if we have an index_col). if len(ic): col_names = [ r[0] if ((r[0] is not None) and r[0] not in self.unnamed_cols) else None for r in header ] else: col_names = [None] * len(header) passed_names = True return names, index_names, col_names, passed_names def _maybe_dedup_names(self, names): # see gh-7160 and gh-9424: this helps to provide # immediate alleviation of the duplicate names # issue and appears to be satisfactory to users, # but ultimately, not needing to butcher the names # would be nice! if self.mangle_dupe_cols: names = list(names) # so we can index # pandas\io\parsers.py:1559: error: Need type annotation for # 'counts' [var-annotated] counts = defaultdict(int) # type: ignore[var-annotated] is_potential_mi = _is_potential_multi_index(names, self.index_col) for i, col in enumerate(names): cur_count = counts[col] while cur_count > 0: counts[col] = cur_count + 1 if is_potential_mi: col = col[:-1] + (f"{col[-1]}.{cur_count}",) else: col = f"{col}.{cur_count}" cur_count = counts[col] names[i] = col counts[col] = cur_count + 1 return names def _maybe_make_multi_index_columns(self, columns, col_names=None): # possibly create a column mi here if _is_potential_multi_index(columns): columns = MultiIndex.from_tuples(columns, names=col_names) return columns def _make_index(self, data, alldata, columns, indexnamerow=False): if not _is_index_col(self.index_col) or not self.index_col: index = None elif not self._has_complex_date_col: index = self._get_simple_index(alldata, columns) index = self._agg_index(index) elif self._has_complex_date_col: if not self._name_processed: (self.index_names, _, self.index_col) = _clean_index_names( list(columns), self.index_col, self.unnamed_cols ) self._name_processed = True index = self._get_complex_date_index(data, columns) index = self._agg_index(index, try_parse_dates=False) # add names for the index if indexnamerow: coffset = len(indexnamerow) - len(columns) # pandas\io\parsers.py:1604: error: Item "None" of "Optional[Any]" # has no attribute "set_names" [union-attr] index = index.set_names(indexnamerow[:coffset]) # type: ignore[union-attr] # maybe create a mi on the columns columns = self._maybe_make_multi_index_columns(columns, self.col_names) return index, columns _implicit_index = False def _get_simple_index(self, data, columns): def ix(col): if not isinstance(col, str): return col raise ValueError(f"Index {col} invalid") to_remove = [] index = [] for idx in self.index_col: i = ix(idx) to_remove.append(i) index.append(data[i]) # remove index items from content and columns, don't pop in # loop for i in sorted(to_remove, reverse=True): data.pop(i) if not self._implicit_index: columns.pop(i) return index def _get_complex_date_index(self, data, col_names): def _get_name(icol): if isinstance(icol, str): return icol if col_names is None: raise ValueError(f"Must supply column order to use {icol!s} as index") for i, c in enumerate(col_names): if i == icol: return c to_remove = [] index = [] for idx in self.index_col: name = _get_name(idx) to_remove.append(name) index.append(data[name]) # remove index items from content and columns, don't pop in # loop for c in sorted(to_remove, reverse=True): data.pop(c) col_names.remove(c) return index def _agg_index(self, index, try_parse_dates=True) -> Index: arrays = [] for i, arr in enumerate(index): if try_parse_dates and self._should_parse_dates(i): arr = self._date_conv(arr) if self.na_filter: col_na_values = self.na_values col_na_fvalues = self.na_fvalues else: col_na_values = set() col_na_fvalues = set() if isinstance(self.na_values, dict): # pandas\io\parsers.py:1678: error: Value of type # "Optional[Any]" is not indexable [index] col_name = self.index_names[i] # type: ignore[index] if col_name is not None: col_na_values, col_na_fvalues = _get_na_values( col_name, self.na_values, self.na_fvalues, self.keep_default_na ) arr, _ = self._infer_types(arr, col_na_values | col_na_fvalues) arrays.append(arr) names = self.index_names index = ensure_index_from_sequences(arrays, names) return index def _convert_to_ndarrays( self, dct, na_values, na_fvalues, verbose=False, converters=None, dtypes=None ): result = {} for c, values in dct.items(): conv_f = None if converters is None else converters.get(c, None) if isinstance(dtypes, dict): cast_type = dtypes.get(c, None) else: # single dtype or None cast_type = dtypes if self.na_filter: col_na_values, col_na_fvalues = _get_na_values( c, na_values, na_fvalues, self.keep_default_na ) else: col_na_values, col_na_fvalues = set(), set() if conv_f is not None: # conv_f applied to data before inference if cast_type is not None: warnings.warn( ( "Both a converter and dtype were specified " f"for column {c} - only the converter will be used" ), ParserWarning, stacklevel=7, ) try: values = lib.map_infer(values, conv_f) except ValueError: mask = algorithms.isin(values, list(na_values)).view(np.uint8) values = lib.map_infer_mask(values, conv_f, mask) cvals, na_count = self._infer_types( values, set(col_na_values) | col_na_fvalues, try_num_bool=False ) else: is_ea = is_extension_array_dtype(cast_type) is_str_or_ea_dtype = is_ea or is_string_dtype(cast_type) # skip inference if specified dtype is object # or casting to an EA try_num_bool = not (cast_type and is_str_or_ea_dtype) # general type inference and conversion cvals, na_count = self._infer_types( values, set(col_na_values) | col_na_fvalues, try_num_bool ) # type specified in dtype param or cast_type is an EA if cast_type and ( not is_dtype_equal(cvals, cast_type) or is_extension_array_dtype(cast_type) ): if not is_ea and na_count > 0: try: if is_bool_dtype(cast_type): raise ValueError( f"Bool column has NA values in column {c}" ) except (AttributeError, TypeError): # invalid input to is_bool_dtype pass cvals = self._cast_types(cvals, cast_type, c) result[c] = cvals if verbose and na_count: print(f"Filled {na_count} NA values in column {c!s}") return result def _infer_types(self, values, na_values, try_num_bool=True): """ Infer types of values, possibly casting Parameters ---------- values : ndarray na_values : set try_num_bool : bool, default try try to cast values to numeric (first preference) or boolean Returns ------- converted : ndarray na_count : int """ na_count = 0 if issubclass(values.dtype.type, (np.number, np.bool_)): mask = algorithms.isin(values, list(na_values)) na_count = mask.sum() if na_count > 0: if is_integer_dtype(values): values = values.astype(np.float64) np.putmask(values, mask, np.nan) return values, na_count if try_num_bool and is_object_dtype(values.dtype): # exclude e.g DatetimeIndex here try: result = lib.maybe_convert_numeric(values, na_values, False) except (ValueError, TypeError): # e.g. encountering datetime string gets ValueError # TypeError can be raised in floatify result = values na_count = parsers.sanitize_objects(result, na_values, False) else: na_count = isna(result).sum() else: result = values if values.dtype == np.object_: na_count = parsers.sanitize_objects(values, na_values, False) if result.dtype == np.object_ and try_num_bool: result = libops.maybe_convert_bool( np.asarray(values), true_values=self.true_values, false_values=self.false_values, ) return result, na_count def _cast_types(self, values, cast_type, column): """ Cast values to specified type Parameters ---------- values : ndarray cast_type : string or np.dtype dtype to cast values to column : string column name - used only for error reporting Returns ------- converted : ndarray """ if is_categorical_dtype(cast_type): known_cats = ( isinstance(cast_type, CategoricalDtype) and cast_type.categories is not None ) if not is_object_dtype(values) and not known_cats: # TODO: this is for consistency with # c-parser which parses all categories # as strings values = astype_nansafe(values, str) cats = Index(values).unique().dropna() values = Categorical._from_inferred_categories( cats, cats.get_indexer(values), cast_type, true_values=self.true_values ) # use the EA's implementation of casting elif is_extension_array_dtype(cast_type): # ensure cast_type is an actual dtype and not a string cast_type = pandas_dtype(cast_type) array_type = cast_type.construct_array_type() try: return array_type._from_sequence_of_strings(values, dtype=cast_type) except NotImplementedError as err: raise NotImplementedError( f"Extension Array: {array_type} must implement " "_from_sequence_of_strings in order to be used in parser methods" ) from err else: try: values = astype_nansafe(values, cast_type, copy=True, skipna=True) except ValueError as err: raise ValueError( f"Unable to convert column {column} to type {cast_type}" ) from err return values def _do_date_conversions(self, names, data): # returns data, columns if self.parse_dates is not None: data, names = _process_date_conversion( data, self._date_conv, self.parse_dates, self.index_col, self.index_names, names, keep_date_col=self.keep_date_col, ) return names, data class CParserWrapper(ParserBase): def __init__(self, src: FilePathOrBuffer, **kwds): self.kwds = kwds kwds = kwds.copy() ParserBase.__init__(self, kwds) # #2442 kwds["allow_leading_cols"] = self.index_col is not False # GH20529, validate usecol arg before TextReader self.usecols, self.usecols_dtype = _validate_usecols_arg(kwds["usecols"]) kwds["usecols"] = self.usecols # open handles self._open_handles(src, kwds) assert self.handles is not None for key in ("storage_options", "encoding", "memory_map", "compression"): kwds.pop(key, None) try: self._reader = parsers.TextReader(self.handles.handle, **kwds) except Exception: self.handles.close() raise self.unnamed_cols = self._reader.unnamed_cols passed_names = self.names is None if self._reader.header is None: self.names = None else: if len(self._reader.header) > 1: # we have a multi index in the columns ( self.names, self.index_names, self.col_names, passed_names, ) = self._extract_multi_indexer_columns( self._reader.header, self.index_names, self.col_names, passed_names ) else: self.names = list(self._reader.header[0]) if self.names is None: if self.prefix: self.names = [ f"{self.prefix}{i}" for i in range(self._reader.table_width) ] else: self.names = list(range(self._reader.table_width)) # gh-9755 # # need to set orig_names here first # so that proper indexing can be done # with _set_noconvert_columns # # once names has been filtered, we will # then set orig_names again to names self.orig_names = self.names[:] if self.usecols: usecols = _evaluate_usecols(self.usecols, self.orig_names) # GH 14671 # assert for mypy, orig_names is List or None, None would error in issubset assert self.orig_names is not None if self.usecols_dtype == "string" and not set(usecols).issubset( self.orig_names ): _validate_usecols_names(usecols, self.orig_names) if len(self.names) > len(usecols): self.names = [ n for i, n in enumerate(self.names) if (i in usecols or n in usecols) ] if len(self.names) < len(usecols): _validate_usecols_names(usecols, self.names) self._validate_parse_dates_presence(self.names) self._set_noconvert_columns() self.orig_names = self.names if not self._has_complex_date_col: if self._reader.leading_cols == 0 and _is_index_col(self.index_col): self._name_processed = True (index_names, self.names, self.index_col) = _clean_index_names( self.names, self.index_col, self.unnamed_cols ) if self.index_names is None: self.index_names = index_names if self._reader.header is None and not passed_names: # pandas\io\parsers.py:1997: error: Argument 1 to "len" has # incompatible type "Optional[Any]"; expected "Sized" # [arg-type] self.index_names = [None] * len( self.index_names # type: ignore[arg-type] ) self._implicit_index = self._reader.leading_cols > 0 def close(self) -> None: super().close() # close additional handles opened by C parser try: self._reader.close() except ValueError: pass def _set_noconvert_columns(self): """ Set the columns that should not undergo dtype conversions. Currently, any column that is involved with date parsing will not undergo such conversions. """ names = self.orig_names if self.usecols_dtype == "integer": # A set of integers will be converted to a list in # the correct order every single time. usecols = list(self.usecols) usecols.sort() elif callable(self.usecols) or self.usecols_dtype not in ("empty", None): # The names attribute should have the correct columns # in the proper order for indexing with parse_dates. usecols = self.names[:] else: # Usecols is empty. # pandas\io\parsers.py:2030: error: Incompatible types in # assignment (expression has type "None", variable has type # "List[Any]") [assignment] usecols = None # type: ignore[assignment] def _set(x): if usecols is not None and is_integer(x): x = usecols[x] if not is_integer(x): # assert for mypy, names is List or None, None would error when calling # .index() assert names is not None x = names.index(x) self._reader.set_noconvert(x) if isinstance(self.parse_dates, list): for val in self.parse_dates: if isinstance(val, list): for k in val: _set(k) else: _set(val) elif isinstance(self.parse_dates, dict): for val in self.parse_dates.values(): if isinstance(val, list): for k in val: _set(k) else: _set(val) elif self.parse_dates: if isinstance(self.index_col, list): for k in self.index_col: _set(k) elif self.index_col is not None: _set(self.index_col) def set_error_bad_lines(self, status): self._reader.set_error_bad_lines(int(status)) def read(self, nrows=None): try: data = self._reader.read(nrows) except StopIteration: if self._first_chunk: self._first_chunk = False names = self._maybe_dedup_names(self.orig_names) index, columns, col_dict = _get_empty_meta( names, self.index_col, self.index_names, dtype=self.kwds.get("dtype"), ) columns = self._maybe_make_multi_index_columns(columns, self.col_names) if self.usecols is not None: columns = self._filter_usecols(columns) col_dict = {k: v for k, v in col_dict.items() if k in columns} return index, columns, col_dict else: self.close() raise # Done with first read, next time raise StopIteration self._first_chunk = False names = self.names if self._reader.leading_cols: if self._has_complex_date_col: raise NotImplementedError("file structure not yet supported") # implicit index, no index names arrays = [] for i in range(self._reader.leading_cols): if self.index_col is None: values = data.pop(i) else: values = data.pop(self.index_col[i]) values = self._maybe_parse_dates(values, i, try_parse_dates=True) arrays.append(values) index = ensure_index_from_sequences(arrays) if self.usecols is not None: names = self._filter_usecols(names) names = self._maybe_dedup_names(names) # rename dict keys data = sorted(data.items()) data = {k: v for k, (i, v) in zip(names, data)} names, data = self._do_date_conversions(names, data) else: # rename dict keys data = sorted(data.items()) # ugh, mutation # assert for mypy, orig_names is List or None, None would error in list(...) assert self.orig_names is not None names = list(self.orig_names) names = self._maybe_dedup_names(names) if self.usecols is not None: names = self._filter_usecols(names) # columns as list alldata = [x[1] for x in data] data = {k: v for k, (i, v) in zip(names, data)} names, data = self._do_date_conversions(names, data) index, names = self._make_index(data, alldata, names) # maybe create a mi on the columns names = self._maybe_make_multi_index_columns(names, self.col_names) return index, names, data def _filter_usecols(self, names): # hackish usecols = _evaluate_usecols(self.usecols, names) if usecols is not None and len(names) != len(usecols): names = [ name for i, name in enumerate(names) if i in usecols or name in usecols ] return names def _get_index_names(self): names = list(self._reader.header[0]) idx_names = None if self._reader.leading_cols == 0 and self.index_col is not None: (idx_names, names, self.index_col) = _clean_index_names( names, self.index_col, self.unnamed_cols ) return names, idx_names def _maybe_parse_dates(self, values, index, try_parse_dates=True): if try_parse_dates and self._should_parse_dates(index): values = self._date_conv(values) return values def TextParser(*args, **kwds): """ Converts lists of lists/tuples into DataFrames with proper type inference and optional (e.g. string to datetime) conversion. Also enables iterating lazily over chunks of large files Parameters ---------- data : file-like object or list delimiter : separator character to use dialect : str or csv.Dialect instance, optional Ignored if delimiter is longer than 1 character names : sequence, default header : int, default 0 Row to use to parse column labels. Defaults to the first row. Prior rows will be discarded index_col : int or list, optional Column or columns to use as the (possibly hierarchical) index has_index_names: bool, default False True if the cols defined in index_col have an index name and are not in the header. na_values : scalar, str, list-like, or dict, optional Additional strings to recognize as NA/NaN. keep_default_na : bool, default True thousands : str, optional Thousands separator comment : str, optional Comment out remainder of line parse_dates : bool, default False keep_date_col : bool, default False date_parser : function, optional skiprows : list of integers Row numbers to skip skipfooter : int Number of line at bottom of file to skip converters : dict, optional Dict of functions for converting values in certain columns. Keys can either be integers or column labels, values are functions that take one input argument, the cell (not column) content, and return the transformed content. encoding : str, optional Encoding to use for UTF when reading/writing (ex. 'utf-8') squeeze : bool, default False returns Series if only one column. infer_datetime_format: bool, default False If True and `parse_dates` is True for a column, try to infer the datetime format based on the first datetime string. If the format can be inferred, there often will be a large parsing speed-up. float_precision : str, optional Specifies which converter the C engine should use for floating-point values. The options are `None` or `high` for the ordinary converter, `legacy` for the original lower precision pandas converter, and `round_trip` for the round-trip converter. .. versionchanged:: 1.2 """ kwds["engine"] = "python" return TextFileReader(*args, **kwds) def count_empty_vals(vals) -> int: return sum(1 for v in vals if v == "" or v is None) class PythonParser(ParserBase): def __init__(self, f: Union[FilePathOrBuffer, List], **kwds): """ Workhorse function for processing nested list into DataFrame """ ParserBase.__init__(self, kwds) self.data: Optional[Iterator[str]] = None self.buf: List = [] self.pos = 0 self.line_pos = 0 self.skiprows = kwds["skiprows"] if callable(self.skiprows): self.skipfunc = self.skiprows else: self.skipfunc = lambda x: x in self.skiprows self.skipfooter = _validate_skipfooter_arg(kwds["skipfooter"]) self.delimiter = kwds["delimiter"] self.quotechar = kwds["quotechar"] if isinstance(self.quotechar, str): self.quotechar = str(self.quotechar) self.escapechar = kwds["escapechar"] self.doublequote = kwds["doublequote"] self.skipinitialspace = kwds["skipinitialspace"] self.lineterminator = kwds["lineterminator"] self.quoting = kwds["quoting"] self.usecols, _ = _validate_usecols_arg(kwds["usecols"]) self.skip_blank_lines = kwds["skip_blank_lines"] self.warn_bad_lines = kwds["warn_bad_lines"] self.error_bad_lines = kwds["error_bad_lines"] self.names_passed = kwds["names"] or None self.has_index_names = False if "has_index_names" in kwds: self.has_index_names = kwds["has_index_names"] self.verbose = kwds["verbose"] self.converters = kwds["converters"] self.dtype = kwds["dtype"] self.thousands = kwds["thousands"] self.decimal = kwds["decimal"] self.comment = kwds["comment"] # Set self.data to something that can read lines. if isinstance(f, list): # read_excel: f is a list self.data = cast(Iterator[str], f) else: self._open_handles(f, kwds) assert self.handles is not None assert hasattr(self.handles.handle, "readline") try: self._make_reader(self.handles.handle) except (csv.Error, UnicodeDecodeError): self.close() raise # Get columns in two steps: infer from data, then # infer column indices from self.usecols if it is specified. self._col_indices = None try: ( self.columns, self.num_original_columns, self.unnamed_cols, ) = self._infer_columns() except (TypeError, ValueError): self.close() raise # Now self.columns has the set of columns that we will process. # The original set is stored in self.original_columns. if len(self.columns) > 1: # we are processing a multi index column ( self.columns, self.index_names, self.col_names, _, ) = self._extract_multi_indexer_columns( self.columns, self.index_names, self.col_names ) # Update list of original names to include all indices. self.num_original_columns = len(self.columns) else: self.columns = self.columns[0] # get popped off for index self.orig_names = list(self.columns) # needs to be cleaned/refactored # multiple date column thing turning into a real spaghetti factory if not self._has_complex_date_col: (index_names, self.orig_names, self.columns) = self._get_index_name( self.columns ) self._name_processed = True if self.index_names is None: self.index_names = index_names self._validate_parse_dates_presence(self.columns) if self.parse_dates: self._no_thousands_columns = self._set_no_thousands_columns() else: self._no_thousands_columns = None if len(self.decimal) != 1: raise ValueError("Only length-1 decimal markers supported") if self.thousands is None: self.nonnum = re.compile(fr"[^-^0-9^{self.decimal}]+") else: self.nonnum = re.compile(fr"[^-^0-9^{self.thousands}^{self.decimal}]+") def _set_no_thousands_columns(self): # Create a set of column ids that are not to be stripped of thousands # operators. noconvert_columns = set() def _set(x): if is_integer(x): noconvert_columns.add(x) else: noconvert_columns.add(self.columns.index(x)) if isinstance(self.parse_dates, list): for val in self.parse_dates: if isinstance(val, list): for k in val: _set(k) else: _set(val) elif isinstance(self.parse_dates, dict): for val in self.parse_dates.values(): if isinstance(val, list): for k in val: _set(k) else: _set(val) elif self.parse_dates: if isinstance(self.index_col, list): for k in self.index_col: _set(k) elif self.index_col is not None: _set(self.index_col) return noconvert_columns def _make_reader(self, f): sep = self.delimiter if sep is None or len(sep) == 1: if self.lineterminator: raise ValueError( "Custom line terminators not supported in python parser (yet)" ) class MyDialect(csv.Dialect): delimiter = self.delimiter quotechar = self.quotechar escapechar = self.escapechar doublequote = self.doublequote skipinitialspace = self.skipinitialspace quoting = self.quoting lineterminator = "\n" dia = MyDialect if sep is not None: dia.delimiter = sep else: # attempt to sniff the delimiter from the first valid line, # i.e. no comment line and not in skiprows line = f.readline() lines = self._check_comments([[line]])[0] while self.skipfunc(self.pos) or not lines: self.pos += 1 line = f.readline() lines = self._check_comments([[line]])[0] # since `line` was a string, lines will be a list containing # only a single string line = lines[0] self.pos += 1 self.line_pos += 1 sniffed = csv.Sniffer().sniff(line) dia.delimiter = sniffed.delimiter # Note: encoding is irrelevant here line_rdr = csv.reader(StringIO(line), dialect=dia) self.buf.extend(list(line_rdr)) # Note: encoding is irrelevant here reader = csv.reader(f, dialect=dia, strict=True) else: def _read(): line = f.readline() pat = re.compile(sep) yield pat.split(line.strip()) for line in f: yield pat.split(line.strip()) reader = _read() # pandas\io\parsers.py:2427: error: Incompatible types in assignment # (expression has type "_reader", variable has type "Union[IO[Any], # RawIOBase, BufferedIOBase, TextIOBase, TextIOWrapper, mmap, None]") # [assignment] self.data = reader # type: ignore[assignment] def read(self, rows=None): try: content = self._get_lines(rows) except StopIteration: if self._first_chunk: content = [] else: self.close() raise # done with first read, next time raise StopIteration self._first_chunk = False # pandas\io\parsers.py:2480: error: Argument 1 to "list" has # incompatible type "Optional[Any]"; expected "Iterable[Any]" # [arg-type] columns = list(self.orig_names) # type: ignore[arg-type] if not len(content): # pragma: no cover # DataFrame with the right metadata, even though it's length 0 names = self._maybe_dedup_names(self.orig_names) index, columns, col_dict = _get_empty_meta( names, self.index_col, self.index_names, self.dtype ) columns = self._maybe_make_multi_index_columns(columns, self.col_names) return index, columns, col_dict # handle new style for names in index count_empty_content_vals = count_empty_vals(content[0]) indexnamerow = None if self.has_index_names and count_empty_content_vals == len(columns): indexnamerow = content[0] content = content[1:] alldata = self._rows_to_cols(content) data = self._exclude_implicit_index(alldata) columns = self._maybe_dedup_names(self.columns) columns, data = self._do_date_conversions(columns, data) data = self._convert_data(data) index, columns = self._make_index(data, alldata, columns, indexnamerow) return index, columns, data def _exclude_implicit_index(self, alldata): names = self._maybe_dedup_names(self.orig_names) if self._implicit_index: excl_indices = self.index_col data = {} offset = 0 for i, col in enumerate(names): while i + offset in excl_indices: offset += 1 data[col] = alldata[i + offset] else: data = {k: v for k, v in zip(names, alldata)} return data # legacy def get_chunk(self, size=None): if size is None: # pandas\io\parsers.py:2528: error: "PythonParser" has no attribute # "chunksize" [attr-defined] size = self.chunksize # type: ignore[attr-defined] return self.read(rows=size) def _convert_data(self, data): # apply converters def _clean_mapping(mapping): """converts col numbers to names""" clean = {} for col, v in mapping.items(): # pandas\io\parsers.py:2537: error: Unsupported right operand # type for in ("Optional[Any]") [operator] if ( isinstance(col, int) and col not in self.orig_names # type: ignore[operator] ): # pandas\io\parsers.py:2538: error: Value of type # "Optional[Any]" is not indexable [index] col = self.orig_names[col] # type: ignore[index] clean[col] = v return clean clean_conv = _clean_mapping(self.converters) if not isinstance(self.dtype, dict): # handles single dtype applied to all columns clean_dtypes = self.dtype else: clean_dtypes = _clean_mapping(self.dtype) # Apply NA values. clean_na_values = {} clean_na_fvalues = {} if isinstance(self.na_values, dict): for col in self.na_values: na_value = self.na_values[col] na_fvalue = self.na_fvalues[col] # pandas\io\parsers.py:2558: error: Unsupported right operand # type for in ("Optional[Any]") [operator] if ( isinstance(col, int) and col not in self.orig_names # type: ignore[operator] ): # pandas\io\parsers.py:2559: error: Value of type # "Optional[Any]" is not indexable [index] col = self.orig_names[col] # type: ignore[index] clean_na_values[col] = na_value clean_na_fvalues[col] = na_fvalue else: clean_na_values = self.na_values clean_na_fvalues = self.na_fvalues return self._convert_to_ndarrays( data, clean_na_values, clean_na_fvalues, self.verbose, clean_conv, clean_dtypes, ) def _infer_columns(self): names = self.names num_original_columns = 0 clear_buffer = True # pandas\io\parsers.py:2580: error: Need type annotation for # 'unnamed_cols' (hint: "unnamed_cols: Set[] = ...") # [var-annotated] unnamed_cols = set() # type: ignore[var-annotated] if self.header is not None: header = self.header if isinstance(header, (list, tuple, np.ndarray)): have_mi_columns = len(header) > 1 # we have a mi columns, so read an extra line if have_mi_columns: header = list(header) + [header[-1] + 1] else: have_mi_columns = False header = [header] # pandas\io\parsers.py:2594: error: Need type annotation for # 'columns' (hint: "columns: List[] = ...") [var-annotated] columns = [] # type: ignore[var-annotated] for level, hr in enumerate(header): try: line = self._buffered_line() while self.line_pos <= hr: line = self._next_line() except StopIteration as err: if self.line_pos < hr: raise ValueError( f"Passed header={hr} but only {self.line_pos + 1} lines in " "file" ) from err # We have an empty file, so check # if columns are provided. That will # serve as the 'line' for parsing if have_mi_columns and hr > 0: if clear_buffer: self._clear_buffer() columns.append([None] * len(columns[-1])) return columns, num_original_columns, unnamed_cols if not self.names: raise EmptyDataError("No columns to parse from file") from err line = self.names[:] this_columns = [] this_unnamed_cols = [] for i, c in enumerate(line): if c == "": if have_mi_columns: col_name = f"Unnamed: {i}_level_{level}" else: col_name = f"Unnamed: {i}" this_unnamed_cols.append(i) this_columns.append(col_name) else: this_columns.append(c) if not have_mi_columns and self.mangle_dupe_cols: # pandas\io\parsers.py:2639: error: Need type annotation # for 'counts' [var-annotated] counts = defaultdict(int) # type: ignore[var-annotated] for i, col in enumerate(this_columns): cur_count = counts[col] while cur_count > 0: counts[col] = cur_count + 1 col = f"{col}.{cur_count}" cur_count = counts[col] this_columns[i] = col counts[col] = cur_count + 1 elif have_mi_columns: # if we have grabbed an extra line, but its not in our # format so save in the buffer, and create an blank extra # line for the rest of the parsing code if hr == header[-1]: lc = len(this_columns) ic = len(self.index_col) if self.index_col is not None else 0 unnamed_count = len(this_unnamed_cols) if lc != unnamed_count and lc - ic > unnamed_count: clear_buffer = False # pandas\io\parsers.py:2663: error: List item 0 has # incompatible type "None"; expected "str" # [list-item] this_columns = [None] * lc # type: ignore[list-item] self.buf = [self.buf[-1]] # pandas\io\parsers.py:2666: error: Argument 1 to "append" of # "list" has incompatible type "List[str]"; expected # "List[None]" [arg-type] columns.append(this_columns) # type: ignore[arg-type] unnamed_cols.update({this_columns[i] for i in this_unnamed_cols}) if len(columns) == 1: num_original_columns = len(this_columns) if clear_buffer: self._clear_buffer() if names is not None: if (self.usecols is not None and len(names) != len(self.usecols)) or ( self.usecols is None and len(names) != len(columns[0]) ): raise ValueError( "Number of passed names did not match " "number of header fields in the file" ) if len(columns) > 1: raise TypeError("Cannot pass names with multi-index columns") if self.usecols is not None: # Set _use_cols. We don't store columns because they are # overwritten. self._handle_usecols(columns, names) else: self._col_indices = None num_original_columns = len(names) columns = [names] else: columns = self._handle_usecols(columns, columns[0]) else: try: line = self._buffered_line() except StopIteration as err: if not names: raise EmptyDataError("No columns to parse from file") from err line = names[:] ncols = len(line) num_original_columns = ncols if not names: if self.prefix: # pandas\io\parsers.py:2711: error: List comprehension has # incompatible type List[str]; expected List[None] [misc] columns = [ [ f"{self.prefix}{i}" # type: ignore[misc] for i in range(ncols) ] ] else: # pandas\io\parsers.py:2713: error: Argument 1 to "list" # has incompatible type "range"; expected "Iterable[None]" # [arg-type] columns = [list(range(ncols))] # type: ignore[arg-type] columns = self._handle_usecols(columns, columns[0]) else: if self.usecols is None or len(names) >= num_original_columns: columns = self._handle_usecols([names], names) num_original_columns = len(names) else: if not callable(self.usecols) and len(names) != len(self.usecols): raise ValueError( "Number of passed names did not match number of " "header fields in the file" ) # Ignore output but set used columns. self._handle_usecols([names], names) columns = [names] num_original_columns = ncols return columns, num_original_columns, unnamed_cols def _handle_usecols(self, columns, usecols_key): """ Sets self._col_indices usecols_key is used if there are string usecols. """ if self.usecols is not None: if callable(self.usecols): col_indices = _evaluate_usecols(self.usecols, usecols_key) elif any(isinstance(u, str) for u in self.usecols): if len(columns) > 1: raise ValueError( "If using multiple headers, usecols must be integers." ) col_indices = [] for col in self.usecols: if isinstance(col, str): try: col_indices.append(usecols_key.index(col)) except ValueError: _validate_usecols_names(self.usecols, usecols_key) else: col_indices.append(col) else: col_indices = self.usecols columns = [ [n for i, n in enumerate(column) if i in col_indices] for column in columns ] self._col_indices = col_indices return columns def _buffered_line(self): """ Return a line from buffer, filling buffer if required. """ if len(self.buf) > 0: return self.buf[0] else: return self._next_line() def _check_for_bom(self, first_row): """ Checks whether the file begins with the BOM character. If it does, remove it. In addition, if there is quoting in the field subsequent to the BOM, remove it as well because it technically takes place at the beginning of the name, not the middle of it. """ # first_row will be a list, so we need to check # that that list is not empty before proceeding. if not first_row: return first_row # The first element of this row is the one that could have the # BOM that we want to remove. Check that the first element is a # string before proceeding. if not isinstance(first_row[0], str): return first_row # Check that the string is not empty, as that would # obviously not have a BOM at the start of it. if not first_row[0]: return first_row # Since the string is non-empty, check that it does # in fact begin with a BOM. first_elt = first_row[0][0] if first_elt != _BOM: return first_row first_row_bom = first_row[0] if len(first_row_bom) > 1 and first_row_bom[1] == self.quotechar: start = 2 quote = first_row_bom[1] end = first_row_bom[2:].index(quote) + 2 # Extract the data between the quotation marks new_row = first_row_bom[start:end] # Extract any remaining data after the second # quotation mark. if len(first_row_bom) > end + 1: new_row += first_row_bom[end + 1 :] else: # No quotation so just remove BOM from first element new_row = first_row_bom[1:] return [new_row] + first_row[1:] def _is_line_empty(self, line): """ Check if a line is empty or not. Parameters ---------- line : str, array-like The line of data to check. Returns ------- boolean : Whether or not the line is empty. """ return not line or all(not x for x in line) def _next_line(self): if isinstance(self.data, list): while self.skipfunc(self.pos): self.pos += 1 while True: try: line = self._check_comments([self.data[self.pos]])[0] self.pos += 1 # either uncommented or blank to begin with if not self.skip_blank_lines and ( self._is_line_empty(self.data[self.pos - 1]) or line ): break elif self.skip_blank_lines: ret = self._remove_empty_lines([line]) if ret: line = ret[0] break except IndexError: raise StopIteration else: while self.skipfunc(self.pos): self.pos += 1 # assert for mypy, data is Iterator[str] or None, would error in next assert self.data is not None next(self.data) while True: orig_line = self._next_iter_line(row_num=self.pos + 1) self.pos += 1 if orig_line is not None: line = self._check_comments([orig_line])[0] if self.skip_blank_lines: ret = self._remove_empty_lines([line]) if ret: line = ret[0] break elif self._is_line_empty(orig_line) or line: break # This was the first line of the file, # which could contain the BOM at the # beginning of it. if self.pos == 1: line = self._check_for_bom(line) self.line_pos += 1 self.buf.append(line) return line def _alert_malformed(self, msg, row_num): """ Alert a user about a malformed row. If `self.error_bad_lines` is True, the alert will be `ParserError`. If `self.warn_bad_lines` is True, the alert will be printed out. Parameters ---------- msg : The error message to display. row_num : The row number where the parsing error occurred. Because this row number is displayed, we 1-index, even though we 0-index internally. """ if self.error_bad_lines: raise ParserError(msg) elif self.warn_bad_lines: base = f"Skipping line {row_num}: " sys.stderr.write(base + msg + "\n") def _next_iter_line(self, row_num): """ Wrapper around iterating through `self.data` (CSV source). When a CSV error is raised, we check for specific error messages that allow us to customize the error message displayed to the user. Parameters ---------- row_num : The row number of the line being parsed. """ try: # assert for mypy, data is Iterator[str] or None, would error in next assert self.data is not None return next(self.data) except csv.Error as e: if self.warn_bad_lines or self.error_bad_lines: msg = str(e) if "NULL byte" in msg or "line contains NUL" in msg: msg = ( "NULL byte detected. This byte " "cannot be processed in Python's " "native csv library at the moment, " "so please pass in engine='c' instead" ) if self.skipfooter > 0: reason = ( "Error could possibly be due to " "parsing errors in the skipped footer rows " "(the skipfooter keyword is only applied " "after Python's csv library has parsed " "all rows)." ) msg += ". " + reason self._alert_malformed(msg, row_num) return None def _check_comments(self, lines): if self.comment is None: return lines ret = [] for line in lines: rl = [] for x in line: if not isinstance(x, str) or self.comment not in x: rl.append(x) else: x = x[: x.find(self.comment)] if len(x) > 0: rl.append(x) break ret.append(rl) return ret def _remove_empty_lines(self, lines): """ Iterate through the lines and remove any that are either empty or contain only one whitespace value Parameters ---------- lines : array-like The array of lines that we are to filter. Returns ------- filtered_lines : array-like The same array of lines with the "empty" ones removed. """ ret = [] for line in lines: # Remove empty lines and lines with only one whitespace value if ( len(line) > 1 or len(line) == 1 and (not isinstance(line[0], str) or line[0].strip()) ): ret.append(line) return ret def _check_thousands(self, lines): if self.thousands is None: return lines return self._search_replace_num_columns( lines=lines, search=self.thousands, replace="" ) def _search_replace_num_columns(self, lines, search, replace): ret = [] for line in lines: rl = [] for i, x in enumerate(line): if ( not isinstance(x, str) or search not in x or (self._no_thousands_columns and i in self._no_thousands_columns) or self.nonnum.search(x.strip()) ): rl.append(x) else: rl.append(x.replace(search, replace)) ret.append(rl) return ret def _check_decimal(self, lines): if self.decimal == _parser_defaults["decimal"]: return lines return self._search_replace_num_columns( lines=lines, search=self.decimal, replace="." ) def _clear_buffer(self): self.buf = [] _implicit_index = False def _get_index_name(self, columns): """ Try several cases to get lines: 0) There are headers on row 0 and row 1 and their total summed lengths equals the length of the next line. Treat row 0 as columns and row 1 as indices 1) Look for implicit index: there are more columns on row 1 than row 0. If this is true, assume that row 1 lists index columns and row 0 lists normal columns. 2) Get index from the columns if it was listed. """ orig_names = list(columns) columns = list(columns) try: line = self._next_line() except StopIteration: line = None try: next_line = self._next_line() except StopIteration: next_line = None # implicitly index_col=0 b/c 1 fewer column names implicit_first_cols = 0 if line is not None: # leave it 0, #2442 # Case 1 if self.index_col is not False: implicit_first_cols = len(line) - self.num_original_columns # Case 0 if next_line is not None: if len(next_line) == len(line) + self.num_original_columns: # column and index names on diff rows self.index_col = list(range(len(line))) self.buf = self.buf[1:] for c in reversed(line): columns.insert(0, c) # Update list of original names to include all indices. orig_names = list(columns) self.num_original_columns = len(columns) return line, orig_names, columns if implicit_first_cols > 0: # Case 1 self._implicit_index = True if self.index_col is None: self.index_col = list(range(implicit_first_cols)) index_name = None else: # Case 2 (index_name, columns_, self.index_col) = _clean_index_names( columns, self.index_col, self.unnamed_cols ) return index_name, orig_names, columns def _rows_to_cols(self, content): col_len = self.num_original_columns if self._implicit_index: col_len += len(self.index_col) max_len = max(len(row) for row in content) # Check that there are no rows with too many # elements in their row (rows with too few # elements are padded with NaN). if max_len > col_len and self.index_col is not False and self.usecols is None: footers = self.skipfooter if self.skipfooter else 0 bad_lines = [] iter_content = enumerate(content) content_len = len(content) content = [] for (i, l) in iter_content: actual_len = len(l) if actual_len > col_len: if self.error_bad_lines or self.warn_bad_lines: row_num = self.pos - (content_len - i + footers) bad_lines.append((row_num, actual_len)) if self.error_bad_lines: break else: content.append(l) for row_num, actual_len in bad_lines: msg = ( f"Expected {col_len} fields in line {row_num + 1}, saw " f"{actual_len}" ) if ( self.delimiter and len(self.delimiter) > 1 and self.quoting != csv.QUOTE_NONE ): # see gh-13374 reason = ( "Error could possibly be due to quotes being " "ignored when a multi-char delimiter is used." ) msg += ". " + reason self._alert_malformed(msg, row_num + 1) # see gh-13320 zipped_content = list(lib.to_object_array(content, min_width=col_len).T) if self.usecols: if self._implicit_index: zipped_content = [ a for i, a in enumerate(zipped_content) if ( i < len(self.index_col) # pandas\io\parsers.py:3159: error: Unsupported right # operand type for in ("Optional[Any]") [operator] or i - len(self.index_col) # type: ignore[operator] in self._col_indices ) ] else: zipped_content = [ # pandas\io\parsers.py:3164: error: Unsupported right # operand type for in ("Optional[Any]") [operator] a for i, a in enumerate(zipped_content) if i in self._col_indices # type: ignore[operator] ] return zipped_content def _get_lines(self, rows=None): lines = self.buf new_rows = None # already fetched some number if rows is not None: # we already have the lines in the buffer if len(self.buf) >= rows: new_rows, self.buf = self.buf[:rows], self.buf[rows:] # need some lines else: rows -= len(self.buf) if new_rows is None: if isinstance(self.data, list): if self.pos > len(self.data): raise StopIteration if rows is None: new_rows = self.data[self.pos :] new_pos = len(self.data) else: new_rows = self.data[self.pos : self.pos + rows] new_pos = self.pos + rows # Check for stop rows. n.b.: self.skiprows is a set. if self.skiprows: new_rows = [ row for i, row in enumerate(new_rows) if not self.skipfunc(i + self.pos) ] lines.extend(new_rows) self.pos = new_pos else: new_rows = [] try: if rows is not None: for _ in range(rows): # assert for mypy, data is Iterator[str] or None, would # error in next assert self.data is not None new_rows.append(next(self.data)) lines.extend(new_rows) else: rows = 0 while True: new_row = self._next_iter_line(row_num=self.pos + rows + 1) rows += 1 if new_row is not None: new_rows.append(new_row) except StopIteration: if self.skiprows: new_rows = [ row for i, row in enumerate(new_rows) if not self.skipfunc(i + self.pos) ] lines.extend(new_rows) if len(lines) == 0: raise self.pos += len(new_rows) self.buf = [] else: lines = new_rows if self.skipfooter: lines = lines[: -self.skipfooter] lines = self._check_comments(lines) if self.skip_blank_lines: lines = self._remove_empty_lines(lines) lines = self._check_thousands(lines) return self._check_decimal(lines) def _make_date_converter( date_parser=None, dayfirst=False, infer_datetime_format=False, cache_dates=True ): def converter(*date_cols): if date_parser is None: strs = parsing.concat_date_cols(date_cols) try: return tools.to_datetime( ensure_object(strs), utc=None, dayfirst=dayfirst, errors="ignore", infer_datetime_format=infer_datetime_format, cache=cache_dates, ).to_numpy() except ValueError: return tools.to_datetime( parsing.try_parse_dates(strs, dayfirst=dayfirst), cache=cache_dates ) else: try: result = tools.to_datetime( date_parser(*date_cols), errors="ignore", cache=cache_dates ) if isinstance(result, datetime.datetime): raise Exception("scalar parser") return result except Exception: try: return tools.to_datetime( parsing.try_parse_dates( parsing.concat_date_cols(date_cols), parser=date_parser, dayfirst=dayfirst, ), errors="ignore", ) except Exception: return generic_parser(date_parser, *date_cols) return converter def _process_date_conversion( data_dict, converter, parse_spec, index_col, index_names, columns, keep_date_col=False, ): def _isindex(colspec): return (isinstance(index_col, list) and colspec in index_col) or ( isinstance(index_names, list) and colspec in index_names ) new_cols = [] new_data = {} orig_names = columns columns = list(columns) date_cols = set() if parse_spec is None or isinstance(parse_spec, bool): return data_dict, columns if isinstance(parse_spec, list): # list of column lists for colspec in parse_spec: if is_scalar(colspec): if isinstance(colspec, int) and colspec not in data_dict: colspec = orig_names[colspec] if _isindex(colspec): continue data_dict[colspec] = converter(data_dict[colspec]) else: new_name, col, old_names = _try_convert_dates( converter, colspec, data_dict, orig_names ) if new_name in data_dict: raise ValueError(f"New date column already in dict {new_name}") new_data[new_name] = col new_cols.append(new_name) date_cols.update(old_names) elif isinstance(parse_spec, dict): # dict of new name to column list for new_name, colspec in parse_spec.items(): if new_name in data_dict: raise ValueError(f"Date column {new_name} already in dict") _, col, old_names = _try_convert_dates( converter, colspec, data_dict, orig_names ) new_data[new_name] = col new_cols.append(new_name) date_cols.update(old_names) data_dict.update(new_data) new_cols.extend(columns) if not keep_date_col: for c in list(date_cols): data_dict.pop(c) new_cols.remove(c) return data_dict, new_cols def _try_convert_dates(parser, colspec, data_dict, columns): colset = set(columns) colnames = [] for c in colspec: if c in colset: colnames.append(c) elif isinstance(c, int) and c not in columns: colnames.append(columns[c]) else: colnames.append(c) new_name = "_".join(str(x) for x in colnames) to_parse = [data_dict[c] for c in colnames if c in data_dict] new_col = parser(*to_parse) return new_name, new_col, colnames def _clean_na_values(na_values, keep_default_na=True): if na_values is None: if keep_default_na: na_values = STR_NA_VALUES else: na_values = set() # pandas\io\parsers.py:3387: error: Need type annotation for # 'na_fvalues' (hint: "na_fvalues: Set[] = ...") [var-annotated] na_fvalues = set() # type: ignore[var-annotated] elif isinstance(na_values, dict): old_na_values = na_values.copy() na_values = {} # Prevent aliasing. # Convert the values in the na_values dictionary # into array-likes for further use. This is also # where we append the default NaN values, provided # that `keep_default_na=True`. for k, v in old_na_values.items(): if not is_list_like(v): v = [v] if keep_default_na: v = set(v) | STR_NA_VALUES na_values[k] = v # pandas\io\parsers.py:3404: error: Incompatible types in assignment # (expression has type "Dict[Any, Any]", variable has type "Set[Any]") # [assignment] na_fvalues = { # type: ignore[assignment] k: _floatify_na_values(v) for k, v in na_values.items() } else: if not is_list_like(na_values): na_values = [na_values] na_values = _stringify_na_values(na_values) if keep_default_na: na_values = na_values | STR_NA_VALUES na_fvalues = _floatify_na_values(na_values) return na_values, na_fvalues def _clean_index_names(columns, index_col, unnamed_cols): if not _is_index_col(index_col): return None, columns, index_col columns = list(columns) cp_cols = list(columns) index_names = [] # don't mutate index_col = list(index_col) for i, c in enumerate(index_col): if isinstance(c, str): index_names.append(c) for j, name in enumerate(cp_cols): if name == c: index_col[i] = j columns.remove(name) break else: name = cp_cols[c] columns.remove(name) index_names.append(name) # Only clean index names that were placeholders. for i, name in enumerate(index_names): if isinstance(name, str) and name in unnamed_cols: # pandas\io\parsers.py:3445: error: No overload variant of # "__setitem__" of "list" matches argument types "int", "None" # [call-overload] index_names[i] = None # type: ignore[call-overload] return index_names, columns, index_col def _get_empty_meta(columns, index_col, index_names, dtype=None): columns = list(columns) # Convert `dtype` to a defaultdict of some kind. # This will enable us to write `dtype[col_name]` # without worrying about KeyError issues later on. if not isinstance(dtype, dict): # if dtype == None, default will be object. default_dtype = dtype or object dtype = defaultdict(lambda: default_dtype) else: # Save a copy of the dictionary. _dtype = dtype.copy() dtype = defaultdict(lambda: object) # Convert column indexes to column names. for k, v in _dtype.items(): col = columns[k] if is_integer(k) else k dtype[col] = v # Even though we have no data, the "index" of the empty DataFrame # could for example still be an empty MultiIndex. Thus, we need to # check whether we have any index columns specified, via either: # # 1) index_col (column indices) # 2) index_names (column names) # # Both must be non-null to ensure a successful construction. Otherwise, # we have to create a generic empty Index. if (index_col is None or index_col is False) or index_names is None: index = Index([]) else: data = [Series([], dtype=dtype[name]) for name in index_names] index = ensure_index_from_sequences(data, names=index_names) index_col.sort() for i, n in enumerate(index_col): columns.pop(n - i) col_dict = {col_name: Series([], dtype=dtype[col_name]) for col_name in columns} return index, columns, col_dict def _floatify_na_values(na_values): # create float versions of the na_values result = set() for v in na_values: try: v = float(v) if not np.isnan(v): result.add(v) except (TypeError, ValueError, OverflowError): pass return result def _stringify_na_values(na_values): """ return a stringified and numeric for these values """ result = [] for x in na_values: result.append(str(x)) result.append(x) try: v = float(x) # we are like 999 here if v == int(v): v = int(v) result.append(f"{v}.0") result.append(str(v)) # pandas\io\parsers.py:3522: error: Argument 1 to "append" of # "list" has incompatible type "float"; expected "str" [arg-type] result.append(v) # type: ignore[arg-type] except (TypeError, ValueError, OverflowError): pass try: # pandas\io\parsers.py:3526: error: Argument 1 to "append" of # "list" has incompatible type "int"; expected "str" [arg-type] result.append(int(x)) # type: ignore[arg-type] except (TypeError, ValueError, OverflowError): pass return set(result) def _get_na_values(col, na_values, na_fvalues, keep_default_na): """ Get the NaN values for a given column. Parameters ---------- col : str The name of the column. na_values : array-like, dict The object listing the NaN values as strings. na_fvalues : array-like, dict The object listing the NaN values as floats. keep_default_na : bool If `na_values` is a dict, and the column is not mapped in the dictionary, whether to return the default NaN values or the empty set. Returns ------- nan_tuple : A length-two tuple composed of 1) na_values : the string NaN values for that column. 2) na_fvalues : the float NaN values for that column. """ if isinstance(na_values, dict): if col in na_values: return na_values[col], na_fvalues[col] else: if keep_default_na: return STR_NA_VALUES, set() return set(), set() else: return na_values, na_fvalues def _get_col_names(colspec, columns): colset = set(columns) colnames = [] for c in colspec: if c in colset: colnames.append(c) elif isinstance(c, int): colnames.append(columns[c]) return colnames class FixedWidthReader(abc.Iterator): """ A reader of fixed-width lines. """ def __init__(self, f, colspecs, delimiter, comment, skiprows=None, infer_nrows=100): self.f = f self.buffer = None self.delimiter = "\r\n" + delimiter if delimiter else "\n\r\t " self.comment = comment if colspecs == "infer": self.colspecs = self.detect_colspecs( infer_nrows=infer_nrows, skiprows=skiprows ) else: self.colspecs = colspecs if not isinstance(self.colspecs, (tuple, list)): raise TypeError( "column specifications must be a list or tuple, " f"input was a {type(colspecs).__name__}" ) for colspec in self.colspecs: if not ( isinstance(colspec, (tuple, list)) and len(colspec) == 2 and isinstance(colspec[0], (int, np.integer, type(None))) and isinstance(colspec[1], (int, np.integer, type(None))) ): raise TypeError( "Each column specification must be " "2 element tuple or list of integers" ) def get_rows(self, infer_nrows, skiprows=None): """ Read rows from self.f, skipping as specified. We distinguish buffer_rows (the first <= infer_nrows lines) from the rows returned to detect_colspecs because it's simpler to leave the other locations with skiprows logic alone than to modify them to deal with the fact we skipped some rows here as well. Parameters ---------- infer_nrows : int Number of rows to read from self.f, not counting rows that are skipped. skiprows: set, optional Indices of rows to skip. Returns ------- detect_rows : list of str A list containing the rows to read. """ if skiprows is None: skiprows = set() buffer_rows = [] detect_rows = [] for i, row in enumerate(self.f): if i not in skiprows: detect_rows.append(row) buffer_rows.append(row) if len(detect_rows) >= infer_nrows: break self.buffer = iter(buffer_rows) return detect_rows def detect_colspecs(self, infer_nrows=100, skiprows=None): # Regex escape the delimiters delimiters = "".join(fr"\{x}" for x in self.delimiter) pattern = re.compile(f"([^{delimiters}]+)") rows = self.get_rows(infer_nrows, skiprows) if not rows: raise EmptyDataError("No rows from which to infer column width") max_len = max(map(len, rows)) mask = np.zeros(max_len + 1, dtype=int) if self.comment is not None: rows = [row.partition(self.comment)[0] for row in rows] for row in rows: for m in pattern.finditer(row): mask[m.start() : m.end()] = 1 shifted = np.roll(mask, 1) shifted[0] = 0 edges = np.where((mask ^ shifted) == 1)[0] edge_pairs = list(zip(edges[::2], edges[1::2])) return edge_pairs def __next__(self): if self.buffer is not None: try: line = next(self.buffer) except StopIteration: self.buffer = None line = next(self.f) else: line = next(self.f) # Note: 'colspecs' is a sequence of half-open intervals. return [line[fromm:to].strip(self.delimiter) for (fromm, to) in self.colspecs] class FixedWidthFieldParser(PythonParser): """ Specialization that Converts fixed-width fields into DataFrames. See PythonParser for details. """ def __init__(self, f, **kwds): # Support iterators, convert to a list. self.colspecs = kwds.pop("colspecs") self.infer_nrows = kwds.pop("infer_nrows") PythonParser.__init__(self, f, **kwds) def _make_reader(self, f): self.data = FixedWidthReader( f, self.colspecs, self.delimiter, self.comment, self.skiprows, self.infer_nrows, ) def _remove_empty_lines(self, lines) -> List: """ Returns the list of lines without the empty ones. With fixed-width fields, empty lines become arrays of empty strings. See PythonParser._remove_empty_lines. """ return [ line for line in lines if any(not isinstance(e, str) or e.strip() for e in line) ] def _refine_defaults_read( dialect: Union[str, csv.Dialect], delimiter: Union[str, object], delim_whitespace: bool, engine: str, sep: Union[str, object], defaults: Dict[str, Any], ): """Validate/refine default values of input parameters of read_csv, read_table. Parameters ---------- dialect : str or csv.Dialect If provided, this parameter will override values (default or not) for the following parameters: `delimiter`, `doublequote`, `escapechar`, `skipinitialspace`, `quotechar`, and `quoting`. If it is necessary to override values, a ParserWarning will be issued. See csv.Dialect documentation for more details. delimiter : str or object Alias for sep. delim_whitespace : bool Specifies whether or not whitespace (e.g. ``' '`` or ``'\t'``) will be used as the sep. Equivalent to setting ``sep='\\s+'``. If this option is set to True, nothing should be passed in for the ``delimiter`` parameter. engine : {{'c', 'python'}} Parser engine to use. The C engine is faster while the python engine is currently more feature-complete. sep : str or object A delimiter provided by the user (str) or a sentinel value, i.e. pandas._libs.lib.no_default. defaults: dict Default values of input parameters. Returns ------- kwds : dict Input parameters with correct values. Raises ------ ValueError : If a delimiter was specified with ``sep`` (or ``delimiter``) and ``delim_whitespace=True``. """ # fix types for sep, delimiter to Union(str, Any) delim_default = defaults["delimiter"] kwds: Dict[str, Any] = {} # gh-23761 # # When a dialect is passed, it overrides any of the overlapping # parameters passed in directly. We don't want to warn if the # default parameters were passed in (since it probably means # that the user didn't pass them in explicitly in the first place). # # "delimiter" is the annoying corner case because we alias it to # "sep" before doing comparison to the dialect values later on. # Thus, we need a flag to indicate that we need to "override" # the comparison to dialect values by checking if default values # for BOTH "delimiter" and "sep" were provided. if dialect is not None: kwds["sep_override"] = delimiter is None and ( sep is lib.no_default or sep == delim_default ) # Alias sep -> delimiter. if delimiter is None: delimiter = sep if delim_whitespace and (delimiter is not lib.no_default): raise ValueError( "Specified a delimiter with both sep and " "delim_whitespace=True; you can only specify one." ) if delimiter is lib.no_default: # assign default separator value kwds["delimiter"] = delim_default else: kwds["delimiter"] = delimiter if engine is not None: kwds["engine_specified"] = True else: kwds["engine"] = "c" kwds["engine_specified"] = False return kwds def _extract_dialect(kwds: Dict[str, Any]) -> Optional[csv.Dialect]: """ Extract concrete csv dialect instance. Returns ------- csv.Dialect or None """ if kwds.get("dialect") is None: return None dialect = kwds["dialect"] if dialect in csv.list_dialects(): dialect = csv.get_dialect(dialect) _validate_dialect(dialect) return dialect MANDATORY_DIALECT_ATTRS = ( "delimiter", "doublequote", "escapechar", "skipinitialspace", "quotechar", "quoting", ) def _validate_dialect(dialect: csv.Dialect) -> None: """ Validate csv dialect instance. Raises ------ ValueError If incorrect dialect is provided. """ for param in MANDATORY_DIALECT_ATTRS: if not hasattr(dialect, param): raise ValueError(f"Invalid dialect {dialect} provided") def _merge_with_dialect_properties( dialect: csv.Dialect, defaults: Dict[str, Any], ) -> Dict[str, Any]: """ Merge default kwargs in TextFileReader with dialect parameters. Parameters ---------- dialect : csv.Dialect Concrete csv dialect. See csv.Dialect documentation for more details. defaults : dict Keyword arguments passed to TextFileReader. Returns ------- kwds : dict Updated keyword arguments, merged with dialect parameters. """ kwds = defaults.copy() for param in MANDATORY_DIALECT_ATTRS: dialect_val = getattr(dialect, param) parser_default = _parser_defaults[param] provided = kwds.get(param, parser_default) # Messages for conflicting values between the dialect # instance and the actual parameters provided. conflict_msgs = [] # Don't warn if the default parameter was passed in, # even if it conflicts with the dialect (gh-23761). if provided != parser_default and provided != dialect_val: msg = ( f"Conflicting values for '{param}': '{provided}' was " f"provided, but the dialect specifies '{dialect_val}'. " "Using the dialect-specified value." ) # Annoying corner case for not warning about # conflicts between dialect and delimiter parameter. # Refer to the outer "_read_" function for more info. if not (param == "delimiter" and kwds.pop("sep_override", False)): conflict_msgs.append(msg) if conflict_msgs: warnings.warn("\n\n".join(conflict_msgs), ParserWarning, stacklevel=2) kwds[param] = dialect_val return kwds def _validate_skipfooter(kwds: Dict[str, Any]) -> None: """ Check whether skipfooter is compatible with other kwargs in TextFileReader. Parameters ---------- kwds : dict Keyword arguments passed to TextFileReader. Raises ------ ValueError If skipfooter is not compatible with other parameters. """ if kwds.get("skipfooter"): if kwds.get("iterator") or kwds.get("chunksize"): raise ValueError("'skipfooter' not supported for iteration") if kwds.get("nrows"): raise ValueError("'skipfooter' not supported with 'nrows'")