csv-detective 0.8.1.dev1674__py3-none-any.whl → 0.8.1.dev1720__py3-none-any.whl

venv/bin/runxlrd.py

@@ -0,0 +1,410 @@
+#!/home/circleci/project/venv/bin/python
+# Copyright (c) 2005-2012 Stephen John Machin, Lingfo Pty Ltd
+# This script is part of the xlrd package, which is released under a
+# BSD-style licence.
+
+from __future__ import print_function
+
+cmd_doc = """
+Commands:
+
+2rows           Print the contents of first and last row in each sheet
+3rows           Print the contents of first, second and last row in each sheet
+bench           Same as "show", but doesn't print -- for profiling
+biff_count[1]   Print a count of each type of BIFF record in the file
+biff_dump[1]    Print a dump (char and hex) of the BIFF records in the file
+fonts           hdr + print a dump of all font objects
+hdr             Mini-overview of file (no per-sheet information)
+hotshot         Do a hotshot profile run e.g. ... -f1 hotshot bench bigfile*.xls
+labels          Dump of sheet.col_label_ranges and ...row... for each sheet
+name_dump       Dump of each object in book.name_obj_list
+names           Print brief information for each NAME record
+ov              Overview of file
+profile         Like "hotshot", but uses cProfile
+show            Print the contents of all rows in each sheet
+version[0]      Print versions of xlrd and Python and exit
+xfc             Print "XF counts" and cell-type counts -- see code for details
+
+[0] means no file arg
+[1] means only one file arg i.e. no glob.glob pattern
+"""
+
+options = None
+if __name__ == "__main__":
+    import xlrd
+    import sys
+    import time
+    import glob
+    import traceback
+    import gc
+
+    from xlrd.timemachine import xrange, REPR
+
+
+    class LogHandler(object):
+
+        def __init__(self, logfileobj):
+            self.logfileobj = logfileobj
+            self.fileheading = None
+            self.shown = 0
+
+        def setfileheading(self, fileheading):
+            self.fileheading = fileheading
+            self.shown = 0
+
+        def write(self, text):
+            if self.fileheading and not self.shown:
+                self.logfileobj.write(self.fileheading)
+                self.shown = 1
+            self.logfileobj.write(text)
+
+    null_cell = xlrd.empty_cell
+
+    def show_row(bk, sh, rowx, colrange, printit):
+        if bk.ragged_rows:
+            colrange = range(sh.row_len(rowx))
+        if not colrange: return
+        if printit: print()
+        if bk.formatting_info:
+            for colx, ty, val, cxfx in get_row_data(bk, sh, rowx, colrange):
+                if printit:
+                    print("cell %s%d: type=%d, data: %r, xfx: %s"
+                        % (xlrd.colname(colx), rowx+1, ty, val, cxfx))
+        else:
+            for colx, ty, val, _unused in get_row_data(bk, sh, rowx, colrange):
+                if printit:
+                    print("cell %s%d: type=%d, data: %r" % (xlrd.colname(colx), rowx+1, ty, val))
+
+    def get_row_data(bk, sh, rowx, colrange):
+        result = []
+        dmode = bk.datemode
+        ctys = sh.row_types(rowx)
+        cvals = sh.row_values(rowx)
+        for colx in colrange:
+            cty = ctys[colx]
+            cval = cvals[colx]
+            if bk.formatting_info:
+                cxfx = str(sh.cell_xf_index(rowx, colx))
+            else:
+                cxfx = ''
+            if cty == xlrd.XL_CELL_DATE:
+                try:
+                    showval = xlrd.xldate_as_tuple(cval, dmode)
+                except xlrd.XLDateError as e:
+                    showval = "%s:%s" % (type(e).__name__, e)
+                    cty = xlrd.XL_CELL_ERROR
+            elif cty == xlrd.XL_CELL_ERROR:
+                showval = xlrd.error_text_from_code.get(cval, '<Unknown error code 0x%02x>' % cval)
+            else:
+                showval = cval
+            result.append((colx, cty, showval, cxfx))
+        return result
+
+    def bk_header(bk):
+        print()
+        print("BIFF version: %s; datemode: %s"
+            % (xlrd.biff_text_from_num[bk.biff_version], bk.datemode))
+        print("codepage: %r (encoding: %s); countries: %r"
+            % (bk.codepage, bk.encoding, bk.countries))
+        print("Last saved by: %r" % bk.user_name)
+        print("Number of data sheets: %d" % bk.nsheets)
+        print("Use mmap: %d; Formatting: %d; On demand: %d"
+            % (bk.use_mmap, bk.formatting_info, bk.on_demand))
+        print("Ragged rows: %d" % bk.ragged_rows)
+        if bk.formatting_info:
+            print("FORMATs: %d, FONTs: %d, XFs: %d"
+                % (len(bk.format_list), len(bk.font_list), len(bk.xf_list)))
+        if not options.suppress_timing:
+            print("Load time: %.2f seconds (stage 1) %.2f seconds (stage 2)"
+                % (bk.load_time_stage_1, bk.load_time_stage_2))
+        print()
+
+    def show_fonts(bk):
+        print("Fonts:")
+        for x in xrange(len(bk.font_list)):
+            font = bk.font_list[x]
+            font.dump(header='== Index %d ==' % x, indent=4)
+
+    def show_names(bk, dump=0):
+        bk_header(bk)
+        if bk.biff_version < 50:
+            print("Names not extracted in this BIFF version")
+            return
+        nlist = bk.name_obj_list
+        print("Name list: %d entries" % len(nlist))
+        for nobj in nlist:
+            if dump:
+                nobj.dump(sys.stdout,
+                    header="\n=== Dump of name_obj_list[%d] ===" % nobj.name_index)
+            else:
+                print("[%d]\tName:%r macro:%r scope:%d\n\tresult:%r\n"
+                    % (nobj.name_index, nobj.name, nobj.macro, nobj.scope, nobj.result))
+
+    def print_labels(sh, labs, title):
+        if not labs:return
+        for rlo, rhi, clo, chi in labs:
+            print("%s label range %s:%s contains:"
+                % (title, xlrd.cellname(rlo, clo), xlrd.cellname(rhi-1, chi-1)))
+            for rx in xrange(rlo, rhi):
+                for cx in xrange(clo, chi):
+                    print("    %s: %r" % (xlrd.cellname(rx, cx), sh.cell_value(rx, cx)))
+
+    def show_labels(bk):
+        # bk_header(bk)
+        hdr = 0
+        for shx in range(bk.nsheets):
+            sh = bk.sheet_by_index(shx)
+            clabs = sh.col_label_ranges
+            rlabs = sh.row_label_ranges
+            if clabs or rlabs:
+                if not hdr:
+                    bk_header(bk)
+                    hdr = 1
+                print("sheet %d: name = %r; nrows = %d; ncols = %d" %
+                    (shx, sh.name, sh.nrows, sh.ncols))
+                print_labels(sh, clabs, 'Col')
+                print_labels(sh, rlabs, 'Row')
+            if bk.on_demand: bk.unload_sheet(shx)
+
+    def show(bk, nshow=65535, printit=1):
+        bk_header(bk)
+        if 0:
+            rclist = xlrd.sheet.rc_stats.items()
+            rclist = sorted(rclist)
+            print("rc stats")
+            for k, v in rclist:
+                print("0x%04x %7d" % (k, v))
+        if options.onesheet:
+            try:
+                shx = int(options.onesheet)
+            except ValueError:
+                shx = bk.sheet_by_name(options.onesheet).number
+            shxrange = [shx]
+        else:
+            shxrange = range(bk.nsheets)
+        # print("shxrange", list(shxrange))
+        for shx in shxrange:
+            sh = bk.sheet_by_index(shx)
+            nrows, ncols = sh.nrows, sh.ncols
+            colrange = range(ncols)
+            anshow = min(nshow, nrows)
+            print("sheet %d: name = %s; nrows = %d; ncols = %d" %
+                (shx, REPR(sh.name), sh.nrows, sh.ncols))
+            if nrows and ncols:
+                # Beat the bounds
+                for rowx in xrange(nrows):
+                    nc = sh.row_len(rowx)
+                    if nc:
+                        sh.row_types(rowx)[nc-1]
+                        sh.row_values(rowx)[nc-1]
+                        sh.cell(rowx, nc-1)
+            for rowx in xrange(anshow-1):
+                if not printit and rowx % 10000 == 1 and rowx > 1:
+                    print("done %d rows" % (rowx-1,))
+                show_row(bk, sh, rowx, colrange, printit)
+            if anshow and nrows:
+                show_row(bk, sh, nrows-1, colrange, printit)
+            print()
+            if bk.on_demand: bk.unload_sheet(shx)
+
+    def count_xfs(bk):
+        bk_header(bk)
+        for shx in range(bk.nsheets):
+            sh = bk.sheet_by_index(shx)
+            nrows = sh.nrows
+            print("sheet %d: name = %r; nrows = %d; ncols = %d" %
+                (shx, sh.name, sh.nrows, sh.ncols))
+            # Access all xfindexes to force gathering stats
+            type_stats = [0, 0, 0, 0, 0, 0, 0]
+            for rowx in xrange(nrows):
+                for colx in xrange(sh.row_len(rowx)):
+                    xfx = sh.cell_xf_index(rowx, colx)
+                    assert xfx >= 0
+                    cty = sh.cell_type(rowx, colx)
+                    type_stats[cty] += 1
+            print("XF stats", sh._xf_index_stats)
+            print("type stats", type_stats)
+            print()
+            if bk.on_demand: bk.unload_sheet(shx)
+
+    def main(cmd_args):
+        import optparse
+        global options
+        usage = "\n%prog [options] command [input-file-patterns]\n" + cmd_doc
+        oparser = optparse.OptionParser(usage)
+        oparser.add_option(
+            "-l", "--logfilename",
+            default="",
+            help="contains error messages")
+        oparser.add_option(
+            "-v", "--verbosity",
+            type="int", default=0,
+            help="level of information and diagnostics provided")
+        oparser.add_option(
+            "-m", "--mmap",
+            type="int", default=-1,
+            help="1: use mmap; 0: don't use mmap; -1: accept heuristic")
+        oparser.add_option(
+            "-e", "--encoding",
+            default="",
+            help="encoding override")
+        oparser.add_option(
+            "-f", "--formatting",
+            type="int", default=0,
+            help="0 (default): no fmt info\n"
+                 "1: fmt info (all cells)\n",
+        )
+        oparser.add_option(
+            "-g", "--gc",
+            type="int", default=0,
+            help="0: auto gc enabled; 1: auto gc disabled, manual collect after each file; 2: no gc")
+        oparser.add_option(
+            "-s", "--onesheet",
+            default="",
+            help="restrict output to this sheet (name or index)")
+        oparser.add_option(
+            "-u", "--unnumbered",
+            action="store_true", default=0,
+            help="omit line numbers or offsets in biff_dump")
+        oparser.add_option(
+            "-d", "--on-demand",
+            action="store_true", default=0,
+            help="load sheets on demand instead of all at once")
+        oparser.add_option(
+            "-t", "--suppress-timing",
+            action="store_true", default=0,
+            help="don't print timings (diffs are less messy)")
+        oparser.add_option(
+            "-r", "--ragged-rows",
+            action="store_true", default=0,
+            help="open_workbook(..., ragged_rows=True)")
+        options, args = oparser.parse_args(cmd_args)
+        if len(args) == 1 and args[0] in ("version", ):
+            pass
+        elif len(args) < 2:
+            oparser.error("Expected at least 2 args, found %d" % len(args))
+        cmd = args[0]
+        xlrd_version = getattr(xlrd, "__VERSION__", "unknown; before 0.5")
+        if cmd == 'biff_dump':
+            xlrd.dump(args[1], unnumbered=options.unnumbered)
+            sys.exit(0)
+        if cmd == 'biff_count':
+            xlrd.count_records(args[1])
+            sys.exit(0)
+        if cmd == 'version':
+            print("xlrd: %s, from %s" % (xlrd_version, xlrd.__file__))
+            print("Python:", sys.version)
+            sys.exit(0)
+        if options.logfilename:
+            logfile = LogHandler(open(options.logfilename, 'w'))
+        else:
+            logfile = sys.stdout
+        mmap_opt = options.mmap
+        mmap_arg = xlrd.USE_MMAP
+        if mmap_opt in (1, 0):
+            mmap_arg = mmap_opt
+        elif mmap_opt != -1:
+            print('Unexpected value (%r) for mmap option -- assuming default' % mmap_opt)
+        fmt_opt = options.formatting | (cmd in ('xfc', ))
+        gc_mode = options.gc
+        if gc_mode:
+            gc.disable()
+        for pattern in args[1:]:
+            for fname in glob.glob(pattern):
+                print("\n=== File: %s ===" % fname)
+                if logfile != sys.stdout:
+                    logfile.setfileheading("\n=== File: %s ===\n" % fname)
+                if gc_mode == 1:
+                    n_unreachable = gc.collect()
+                    if n_unreachable:
+                        print("GC before open:", n_unreachable, "unreachable objects")
+                try:
+                    t0 = time.time()
+                    bk = xlrd.open_workbook(
+                        fname,
+                        verbosity=options.verbosity, logfile=logfile,
+                        use_mmap=mmap_arg,
+                        encoding_override=options.encoding,
+                        formatting_info=fmt_opt,
+                        on_demand=options.on_demand,
+                        ragged_rows=options.ragged_rows,
+                    )
+                    t1 = time.time()
+                    if not options.suppress_timing:
+                        print("Open took %.2f seconds" % (t1-t0,))
+                except xlrd.XLRDError as e:
+                    print("*** Open failed: %s: %s" % (type(e).__name__, e))
+                    continue
+                except KeyboardInterrupt:
+                    print("*** KeyboardInterrupt ***")
+                    traceback.print_exc(file=sys.stdout)
+                    sys.exit(1)
+                except BaseException as e:
+                    print("*** Open failed: %s: %s" % (type(e).__name__, e))
+                    traceback.print_exc(file=sys.stdout)
+                    continue
+                t0 = time.time()
+                if cmd == 'hdr':
+                    bk_header(bk)
+                elif cmd == 'ov': # OverView
+                    show(bk, 0)
+                elif cmd == 'show': # all rows
+                    show(bk)
+                elif cmd == '2rows': # first row and last row
+                    show(bk, 2)
+                elif cmd == '3rows': # first row, 2nd row and last row
+                    show(bk, 3)
+                elif cmd == 'bench':
+                    show(bk, printit=0)
+                elif cmd == 'fonts':
+                    bk_header(bk)
+                    show_fonts(bk)
+                elif cmd == 'names': # named reference list
+                    show_names(bk)
+                elif cmd == 'name_dump': # named reference list
+                    show_names(bk, dump=1)
+                elif cmd == 'labels':
+                    show_labels(bk)
+                elif cmd == 'xfc':
+                    count_xfs(bk)
+                else:
+                    print("*** Unknown command <%s>" % cmd)
+                    sys.exit(1)
+                del bk
+                if gc_mode == 1:
+                    n_unreachable = gc.collect()
+                    if n_unreachable:
+                        print("GC post cmd:", fname, "->", n_unreachable, "unreachable objects")
+                if not options.suppress_timing:
+                    t1 = time.time()
+                    print("\ncommand took %.2f seconds\n" % (t1-t0,))
+
+        return None
+
+    av = sys.argv[1:]
+    if not av:
+        main(av)
+    firstarg = av[0].lower()
+    if firstarg == "hotshot":
+        import hotshot
+        import hotshot.stats
+        av = av[1:]
+        prof_log_name = "XXXX.prof"
+        prof = hotshot.Profile(prof_log_name)
+        # benchtime, result = prof.runcall(main, *av)
+        result = prof.runcall(main, *(av, ))
+        print("result", repr(result))
+        prof.close()
+        stats = hotshot.stats.load(prof_log_name)
+        stats.strip_dirs()
+        stats.sort_stats('time', 'calls')
+        stats.print_stats(20)
+    elif firstarg == "profile":
+        import cProfile
+        av = av[1:]
+        cProfile.run('main(av)', 'YYYY.prof')
+        import pstats
+        p = pstats.Stats('YYYY.prof')
+        p.strip_dirs().sort_stats('cumulative').print_stats(30)
+    else:
+        main(av)

csv_detective-0.8.1.dev1674.data/data/share/csv_detective/CHANGELOG.md

@@ -1,186 +0,0 @@
-# Changelog
-
-## Current (in progress)
-
-- Refactor label testing [#119](https://github.com/datagouv/csv-detective/pull/119)
-- Refactor repo metadata and requirements [#120](https://github.com/datagouv/csv-detective/pull/120) [#122](https://github.com/datagouv/csv-detective/pull/122) [#135](https://github.com/datagouv/csv-detective/pull/135) [#136](https://github.com/datagouv/csv-detective/pull/136) [#138](https://github.com/datagouv/csv-detective/pull/138)
-- Better URL detection [#121](https://github.com/datagouv/csv-detective/pull/121)
-- For big files, analyse on sample then validate on whole file [#124](https://github.com/datagouv/csv-detective/pull/124) [#129](https://github.com/datagouv/csv-detective/pull/129)
-- Fix imports [#125](https://github.com/datagouv/csv-detective/pull/125) [#126](https://github.com/datagouv/csv-detective/pull/126) [#127](https://github.com/datagouv/csv-detective/pull/127) [#128](https://github.com/datagouv/csv-detective/pull/128)
-- Split aware and naive datetimes for hydra to cast them separately [#130](https://github.com/datagouv/csv-detective/pull/130)
-- Validate using the testing function, to consider PROPORTIONS [#131](https://github.com/datagouv/csv-detective/pull/131)
-- Remove `datetime_iso` format due to ambiguous cast in db (can be naive or aware) [#132](https://github.com/datagouv/csv-detective/pull/132)
-- Add `lonlat_wgs` format and handle optional brackets for `latlon_wgs` [#133](https://github.com/datagouv/csv-detective/pull/133)
-- Refactor format prioritizing [#134](https://github.com/datagouv/csv-detective/pull/134)
-
-## 0.8.0 (2025-05-20)
-
-- New function that creates a csv from a list of fields and constraints, or from a TableSchema [#101](https://github.com/datagouv/csv-detective/pull/101)
-- Enable outputing loaded dataframe [#102](https://github.com/datagouv/csv-detective/pull/102)
-- Better naming, hint types and minor refactors [#103](https://github.com/datagouv/csv-detective/pull/103)
-- The returned dataframe has its columns properly cast to the detected types [#104](https://github.com/datagouv/csv-detective/pull/104)
-- Raise an error if the encoding could not be guessed [#106](https://github.com/datagouv/csv-detective/pull/106)
-- Fix CLI and minio routine [#107](https://github.com/datagouv/csv-detective/pull/107)
-- Allow to only specify tests to skip ("all but...") [#108](https://github.com/datagouv/csv-detective/pull/108)
-- Fix bool casting [#109](https://github.com/datagouv/csv-detective/pull/109)
-- Handle csv.gz files [#110](https://github.com/datagouv/csv-detective/pull/110)
-- Refactor file tests [#110](https://github.com/datagouv/csv-detective/pull/110)
-- Restructure repo (breaking changes) [#111](https://github.com/datagouv/csv-detective/pull/111)
-- Add validation function and associated flow [#112](https://github.com/datagouv/csv-detective/pull/112)
-- Better float detection [#113](https://github.com/datagouv/csv-detective/pull/113)
-- Refactor fields tests [#114](https://github.com/datagouv/csv-detective/pull/114)
-- Better code waldec and add code import [#116](https://github.com/datagouv/csv-detective/pull/116)
-- Better validation and refactors [#117](https://github.com/datagouv/csv-detective/pull/117)
-- Fix validation [#118](https://github.com/datagouv/csv-detective/pull/118)
-
-## 0.7.4 (2024-11-15)
-
-- Enable calling main functions from base [#97](https://github.com/datagouv/csv-detective/pull/97)
-- Better detection of ints and floats [#94](https://github.com/datagouv/csv-detective/pull/94)
-- Better handle NaN values [#96](https://github.com/datagouv/csv-detective/pull/96)
-- Reshape exemple.py, clean up code and improve changelog [#98](https://github.com/datagouv/csv-detective/pull/98)
-
-## 0.7.3 (2024-10-07)
-
-- Refactor tests import, now using folder arborescence instead of pre-made file [#93](https://github.com/datagouv/csv-detective/pull/93)
-- Fix inversion (count<=>value) in profile [#95](https://github.com/datagouv/csv-detective/pull/95)
-
-## 0.7.2 (2024-08-27)
-
-- Outsource many formats to fr-format library [#87](https://github.com/datagouv/csv-detective/pull/87)
-- Better date detection [#89](https://github.com/datagouv/csv-detective/pull/89)
-- Update dependencies to make tests pass [#81](https://github.com/datagouv/csv-detective/pull/81)
-- Update readme [#81](https://github.com/datagouv/csv-detective/pull/81)
-- Hint type [#81](https://github.com/datagouv/csv-detective/pull/81)
-- Minor refactors [#81](https://github.com/datagouv/csv-detective/pull/81)
-
-## 0.7.1 (2024-03-27)
-
-- Fixes after production release in hydra [#80](https://github.com/datagouv/csv-detective/pull/80)
-
-## 0.7.0 (2024-03-21)
-
-- Handle other file formats: xls, xlsx, ods (and more) and analysis through URLs [#73](https://github.com/datagouv/csv-detective/pull/73)
-- Handle files with no extension (cc hydra) [#79](https://github.com/datagouv/csv-detective/pull/79)
-
-## 0.6.8 (2024-01-18)
-
-- prevent exporting NaN values in profile [#72](https://github.com/datagouv/csv-detective/pull/72)
-- raise ValueError if analyzed file has various number of columns across first rows [#72](https://github.com/datagouv/csv-detective/pull/72)
-
-## 0.6.7 (2024-01-15)
-
-- Add logs for columns that would take too much time within a specific test [#70](https://github.com/datagouv/csv-detective/pull/70)
-- Refactor some tests to improve performances and make detection more accurate [#69](https://github.com/datagouv/csv-detective/pull/69)
-- Try alternative ways to clean text [#71](https://github.com/datagouv/csv-detective/pull/71)
-
-## 0.6.6 (2023-11-24)
-
-- Change setup.py to better convey dependencies [#67](https://github.com/datagouv/csv-detective/pull/67)
-
-## 0.6.5 (2023-11-17)
-
-- Change encoding detection for faust-cchardet (forked from cchardet) [#66](https://github.com/etalab/csv-detective/pull/66)
-
-## 0.6.4 (2023-10-18)
-
-- Better handling of ints and floats (now not accepting blanks and "+" in string) [#62](https://github.com/etalab/csv-detective/pull/62)
-
-## 0.6.3 (2023-03-23)
-
-- Faster routine [#59](https://github.com/etalab/csv-detective/pull/59)
-
-## 0.6.2 (2023-02-10)
-
-- Catch OverflowError for latitude and longitude checks [#58](https://github.com/etalab/csv-detective/pull/58)
-
-## 0.6.0 (2023-02-10)
-
-- Add CI and upgrade dependencies [#49](https://github.com/etalab/csv-detective/pull/49)
-- Shuffle data before analysis [#56](https://github.com/etalab/csv-detective/pull/56)
-- Better discrimination between `code_departement` and `code_region` [#56](https://github.com/etalab/csv-detective/pull/56)
-- Add schema in output analysis [#57](https://github.com/etalab/csv-detective/pull/57)
-
-## 0.4.7 [#51](https://github.com/etalab/csv-detective/pull/51)
-
-- Allow possibility to analyze entire file instead of a limited number of rows [#48](https://github.com/etalab/csv-detective/pull/48)
-- Better boolean detection [#42](https://github.com/etalab/csv-detective/issues/42)
-- Differentiate python types and format for `date` and `datetime` [#43](https://github.com/etalab/csv-detective/issues/43)
-- Better `code_departement` and `code_commune_insee` detection [#44](https://github.com/etalab/csv-detective/issues/44)
-- Fix header line (`header_row_idx`) detection [#44](https://github.com/etalab/csv-detective/issues/44)
-- Allow possibility to get profile of csv [#46](https://github.com/etalab/csv-detective/issues/46)
-
-## 0.4.6 [#39](https://github.com/etalab/csv-detective/pull/39)
-
-- Fix tests
-- Prioritise lat / lon FR detection over more generic lat / lon.
-- To reduce false positives, prevent detection of the following if label detection is missing: `['code_departement', 'code_commune_insee', 'code_postal', 'latitude_wgs', 'longitude_wgs', 'latitude_wgs_fr_metropole', 'longitude_wgs_fr_metropole', 'latitude_l93', 'longitude_l93']`
-- Lower threshold of label detection so that if one relevant is detected in the label, it boosts the detection score.
-- Add ISO country alpha-3 and numeric detection
-- include camel case parsing in _process_text function
-- Support optional brackets in latlon format
-
-## 0.4.5 [#29](https://github.com/etalab/csv-detective/pull/29)
-
-- Use `netloc` instead of `url` in location dict
-
-## 0.4.4 [#24] (https://github.com/etalab/csv-detective/pull/28)
-
-- Prevent crash on empty CSVs
-- Add optional arguments encoding and sep to routine and routine_minio functions
-- Field detection improvements (code_csp_insee and datetime RFC 822)
-- Schema generation improvements with examples
-
-
-## 0.4.3 [#24] (https://github.com/etalab/csv-detective/pull/24)
-
-- Add uuid and MongoID detection
-- Add new function dedicated to interaction with minio data
-- Add table schema automatic generation (only on minio data)
-- Modification of calculated score (consider label detection as a boost for score)
-
-## 0.4.2 [#22] (https://github.com/etalab/csv-detective/pull/22)
-
-Add type detection by header name
-
-## 0.4.1 [#19] (https://github.com/etalab/csv-detective/pull/19)
-
-Fix bug
- * num_rows was causing problem when it was fix to other value than default - Fixed
-
-## 0.4.0 [#18] (https://github.com/etalab/csv_detective/pull/18)
-
-Add detailed output possibility
-
-Details :
- * two modes now for output report : "LIMITED" and "ALL"
- * "ALL" option give user information on found proportion for each column types and each columns
-
-## 0.3.0 [#15] (https://github.com/etalab/csv_detective/pull/15)
-
-Fix bugs
-
-Details :
- * Facilitate ML Integration
- * Add column types detection
- * Fix documentation
-
-## 0.2.1 - [#2](https://github.com/etalab/csv_detective/pull/2)
-
-Add continuous integration
-
-Details :
- * Add configuration for CircleCI
- * Add `CONTRIBUTING.md`
- * Push automatically new versions to PyPI
- * Use semantic versioning
-
-## 0.2 - [#1](https://github.com/etalab/csv_detective/pull/1)
-
-Port from python2 to python3
-
-Details :
- * Add license AGPLv3
- * Update requirements
-
-## 0.1