3
6cY @ s d Z ddlmZ ddlZddlZddlZddlZddlZddlm Z ddl
m Z ddl m
Z
mZmZ ddlmZ dd lmZ d
d gZG d d
d
eZG dd deZG dd d eZG dd deZG dd deZe Zd dd
Z G dd deZ e Z dd Z dd Z dS ) a
This module offers a generic date/time string parser which is able to parse
most known formats to represent a date and/or time.
This module attempts to be forgiving with regards to unlikely input formats,
returning a datetime object even for dates which are ambiguous. If an element
of a date/time stamp is omitted, the following rules are applied:
- If AM or PM is left unspecified, a 24-hour clock is assumed, however, an hour
on a 12-hour clock (``0 <= hour <= 12``) *must* be specified if AM or PM is
specified.
- If a time zone is omitted, a timezone-naive datetime is returned.
If any other elements are missing, they are taken from the
:class:`datetime.datetime` object passed to the parameter ``default``. If this
results in a day number exceeding the valid number of days per month, the
value falls back to the end of the month.
Additional resources about date/time string formats can be found below:
- `A summary of the international standard date and time notation
`_
- `W3C Date and Time Formats `_
- `Time Formats (Planetary Rings Node) `_
- `CPAN ParseDate module
`_
- `Java SimpleDateFormat Class
`_
)unicode_literalsN)StringIO)
monthrange) text_type binary_type
integer_types )
relativedelta)tzparse
parserinfoc @ sn e Zd ZejdZdd Zdd Zdd Zdd Z d
d Z
e d d
Z e dd Z
e dd Ze dd ZdS )_timelexz([.,])c C sd t |tr|j }t |tr$t|}t|dd d krHtdj|jj d|| _
g | _ g | _ d| _
d S )Nreadz8Parser must be a string or character stream, not {itype})ZitypeF)
isinstancer decoder r getattr TypeErrorformat __class____name__instream charstack
tokenstackeof)selfr r /usr/lib/python3.6/parser.py__init__4 s
z_timelex.__init__c C s | j r| j jdS d}d}d}x| js | jr>| jjd}n&| jjd}x|dkrb| jjd}qLW |srd| _P q"|s|}| j|rd}n$| j|rd}n| j|rd }P nP q"|dk rd}| j|r||7 }n$|d
kr||7 }d }n| jj | P q"|dkrX| j|r||7 }n>|d
ks:|d krHt
|d
krH||7 }d}n| jj | P q"|d krd}|d
ks|| j|r||7 }n6| j|r|d d
kr||7 }d}n| jj | P q"|dkr"|d
ks| j|r||7 }q"| j|r|d d
kr||7 }d }q"| jj | P q"W |dkr|sN|j d
dksN|d dkr| j j
|}|d }x(|dd D ]}|rp| j j | qpW |dkr|j d
dkr|jd d
}|S )a
This function breaks the time string into lexical units (tokens), which
can be parsed by the parser. Lexical units are demarcated by changes in
the character set, so any continuous string of letters is considered
one unit, any continuous string of numbers is considered one unit.
The main complication arises from the fact that dots ('.') can be used
both as separators (e.g. "Sep.20.2009") or decimal points (e.g.
"4:30:21.447"). As such, it is necessary to read the full context of
any dot-separated strings before breaking it into tokens; as such, this
function maintains a "token stack", for when the ambiguous context
demands that multiple tokens be parsed at once.
r FNr Ta0 .a., 0.z.,r' )r# r& r' )r popr r r r iswordisnumisspaceappendlencount_split_decimalsplitreplace)r Z seenletterstokenstatenextcharltokr r r get_tokenD s
"
z_timelex.get_tokenc C s | S )Nr )r r r r __iter__ s z_timelex.__iter__c C s | j }|d krt|S )N)r7
StopIteration)r r2 r r r __next__ s z_timelex.__next__c C s | j S )N)r: )r r r r next s z
_timelex.nextc C s t | |S )N)list)clssr r r r0 s z_timelex.splitc C s |j S )z5 Whether or not the next character is part of a word )isalpha)r= r4 r r r r) s z_timelex.iswordc C s |j S )z0 Whether the next character is part of a number )isdigit)r= r4 r r r r* s z_timelex.isnumc C s |j S )z* Whether the next character is whitespace )r+ )r= r4 r r r r+ s z_timelex.isspaceN)r
__module__ __qualname__recompiler/ r r7 r8 r: r; classmethodr0 r) r* r+ r r r r r
0 s
m r
c @ s, e Zd Zdd Zdd Zdd Zdd Zd S )
_resultbasec C s x| j D ]}t| |d qW d S )N) __slots__setattr)r attrr r r r s z_resultbase.__init__c C sN g }x6| j D ],}t| |}|d k r |jd|t|f q W d|dj|f S )Nz%s=%sz%s(%s)z, )rG r r, reprjoin)r Z classnamer5 rI valuer r r _repr s
z_resultbase._reprc s t fdd jD S )Nc 3 s | ]}t |d k V qd S )N)r ).0rI )r r r s z&_resultbase.__len__..)sumrG )r r )r r __len__ s z_resultbase.__len__c C s | j | jjS )N)rM r r )r r r r __repr__ s z_resultbase.__repr__N)r rA rB r rM rQ rR r r r r rF s rF c @ s e Zd ZdZdddddddd d
d d d
ddddddgZdcdddedfdgdhdigZdjdkdldmdndodpdqdrdsdtdug ZdvdwdxgZdydzgZdFdGdHgZ dgZ
i Z d{dJdKZ dLdM Z
dNdO ZdPdQ ZdRdS ZdTdU ZdVdW ZdXdY ZdZd[ Zd\d] Zd|d^d_Zd`da ZdbS )}r a
Class which handles what inputs are accepted. Subclass this to customize
the language and acceptable values for each parameter.
:param dayfirst:
Whether to interpret the first value in an ambiguous 3-integer date
(e.g. 01/05/09) as the day (``True``) or month (``False``). If
``yearfirst`` is set to ``True``, this distinguishes between YDM
and YMD. Default is ``False``.
:param yearfirst:
Whether to interpret the first value in an ambiguous 3-integer date
(e.g. 01/05/09) as the year. If ``True``, the first number is taken
to be the year, otherwise the last number is taken to be the year.
Default is ``False``.
r! r" r$ ;-/'ZatZonandZadmtZofstZndZrdZthMonMondayTueTuesdayWed WednesdayThuThursdayFriFridaySatSaturdaySunSundayJanJanuaryFebFebruaryMarMarchAprAprilMayJunJuneJulJulyAugAugustSepSept SeptemberOctOctoberNovNovemberDecDecemberhhourhoursminuteminutesr> secondsecondsamr pmpUTCZGMTZFc C s | j | j| _| j | j| _| j | j| _| j | j| _| j | j | _
| j | j | _ | j | j
| _|| _|| _tj j| _| jd d | _d S )Nd )_convertJUMP_jumpWEEKDAYS _weekdaysMONTHS_monthsHMS_hmsAMPM_ampmUTCZONE_utczonePERTAIN_pertaindayfirst yearfirsttimeZ localtimeZtm_year_year_century)r r r r r r r s zparserinfo.__init__c C sP i }xFt |D ]:\}}t|tr.)r- minr keysr KeyError)r r r r r weekday7 s zparserinfo.weekdayc C sL t |tdd | jj D krHy| j|j d S tk
rF Y nX d S )Nc s s | ]}t |V qd S )N)r- )rN r r r r rO @ s z#parserinfo.month..r )r- r r r r r )r r r r r month? s zparserinfo.monthc C s( y| j |j S tk
r" d S X d S )N)r r r )r r r r r hmsG s zparserinfo.hmsc C s( y| j |j S tk
r" d S X d S )N)r r r )r r r r r ampmM s zparserinfo.ampmc C s |j | jkS )N)r r )r r r r r pertainS s zparserinfo.pertainc C s |j | jkS )N)r r )r r r r r utczoneV s zparserinfo.utczonec C s || j krdS | jj|S )Nr )r TZOFFSETget)r r r r r tzoffsetY s
zparserinfo.tzoffsetc C sJ |dk rF| rF|| j 7 }t|| j dkrF|| jk r>|d7 }n|d8 }|S )Nr 2 )r absr )r yearcentury_specifiedr r r convertyear_ s
zparserinfo.convertyearc C sl |j d k r | j|j |j|_ |jdkr.|j s8|jdkrFd|_d|_n"|jdkrh|jrh| j|jrhd|_dS )Nr r r T)r r r r tznamer )r resr r r validatei s
zparserinfo.validateN)r[ r\ )r] r^ )r_ r` )ra rb )rc rd )re rf )rg rh )ri rj )rk rl )rm rn )ro rp )rq rq )rr rs )rt ru )rv rw )rx ry rz )r{ r| )r} r~ )r r )r r r )rX r r )r> r r )r r )r r )FF)F)r rA rB __doc__r r r r r r r r r r r r r r r r r r r r r r r r r sV
c sP e Zd Z fddZedd Zedd Zdd Z fd d
Zd d Z Z
S )
_ymdc s$ t | j| j|| d| _|| _d S )NF)superr r r tzstr)r r argskwargs)r r r r w s z
_ymd.__init__c C s& y t | |kS tk
r dS X d S )NF)int
ValueError)r2 r r r r token_could_be_year| s z_ymd.token_could_be_yearc s fdd|D S )Nc s g | ]}t j| r|qS r )r r )rN r2 )r r r
s z3_ymd.find_potential_year_tokens..r )r tokensr )r r find_potential_year_tokens s z _ymd.find_potential_year_tokensc C sF x@t | D ]4\}}tj||}t|dkr
t|d dkr
|S q
W dS )zk
attempt to deduce if a pre 100 year was lost
due to padded zeros being taken off
r r r% N)r r r r- )r r indexr2 Zpotential_year_tokensr r r find_probable_year_index s z _ymd.find_probable_year_indexc sN t |dr&|j r4t|dkr4d| _n|dkr4d| _t| j| jt| d S )NrQ r% Tr )hasattrr@ r- r r r r, r )r val)r r r r, s
z _ymd.appendc C s, t | }d\}}}|dkr&tdn|dks>|d kr|dkr|d
krT| | }| |= |dksd|d kr| d dkrz| d }n| d }n|dkr| d dkr| \}}n8| d dkr| \}}n"|r| d dkr| \}}n| \}}nB|dkr"|dkr| \}}}n |dkrF| d dks.|r:| d dkr:| \}}}n
| \}}}n|dkrv| d dkrj| \}}}n
| \}}}n| d dks| jtj| jdks|r| d dkr| d dkr|r| d dkr| \}}}n
| \}}}n8| d dks |r| d dkr| \}}}n
| \}}}|||fS ) N zMore than three YMD valuesr r% r )NNNr' r' r' )r- r r r
r0 r )r mstridxr r Zlen_ymdr r dayr r r resolve_ymd sR
"
" "
z_ymd.resolve_ymd) r rA rB r staticmethodr r r r, r
__classcell__r r )r r r v s
r c @ sF e Zd Zd
ddZdddZG dd deZdd d
Zed d Z dS )parserNc C s |pt | _d S )N)r info)r r r r r r s zparser.__init__Fc K sV |dkr t j j jddddd}| j|f|\}}|dkrBtdt|dkrVtdi }x&dD ] } t|| }
|
dk r`|
|| < q`W d|kr|jdkr|jn|j} |jdkr|jn|j} |j dkr|j n|j }
|
t
| | d
krt
| | d
|d< |jf |}|j dk r$|j r$|t j |j d }|s8t
|tjsJ|r|j|krt
|tjrh||j|j}n |j|j}t
|t jr|}n|jdkr|jtj d}n |jr8|jtj|j|jd}|jddrN||fS |S dS )aV
Parse the date/time string into a :class:`datetime.datetime` object.
:param timestr:
Any date/time string using the supported formats.
:param default:
The default datetime object, if this is a datetime object and not
``None``, elements specified in ``timestr`` replace elements in the
default object.
:param ignoretz:
If set ``True``, time zones in parsed strings are ignored and a
naive :class:`datetime.datetime` object is returned.
:param tzinfos:
Additional time zone names / aliases which may be present in the
string. This argument maps time zone names (and optionally offsets
from those time zones) to time zones. This parameter can be a
dictionary with timezone aliases mapping time zone names to time
zones or a function taking two parameters (``tzname`` and
``tzoffset``) and returning a time zone.
The timezones to which the names are mapped can be an integer
offset from UTC in minutes or a :class:`tzinfo` object.
.. doctest::
:options: +NORMALIZE_WHITESPACE
>>> from dateutil.parser import parse
>>> from dateutil.tz import gettz
>>> tzinfos = {"BRST": -10800, "CST": gettz("America/Chicago")}
>>> parse("2012-01-19 17:21:00 BRST", tzinfos=tzinfos)
datetime.datetime(2012, 1, 19, 17, 21, tzinfo=tzoffset(u'BRST', -10800))
>>> parse("2012-01-19 17:21:00 CST", tzinfos=tzinfos)
datetime.datetime(2012, 1, 19, 17, 21,
tzinfo=tzfile('/usr/share/zoneinfo/America/Chicago'))
This parameter is ignored if ``ignoretz`` is set.
:param **kwargs:
Keyword arguments as passed to ``_parse()``.
:return:
Returns a :class:`datetime.datetime` object or, if the
``fuzzy_with_tokens`` option is ``True``, returns a tuple, the
first element being a :class:`datetime.datetime` object, the second
a tuple containing the fuzzy tokens.
:raises ValueError:
Raised for invalid or unknown string format, if the provided
:class:`tzinfo` is not in a valid format, or if an invalid date
would be created.
:raises TypeError:
Raised for non-string or character stream input.
:raises OverflowError:
Raised if the parsed date exceeds the largest valid C integer on
your system.
Nr )r r r microsecondzUnknown string formatz String does not contain a date.r r r r r r r r )r z9Offset must be tzinfo subclass, tz string, or int offset.)tzinfofuzzy_with_tokensF)r r r r r r r )datetimeZnowr1 _parser r- r r r r r r r r collectionsCallabler r r r r r
r r r ZtzlocalZtzutc)r timestrdefaultZignoretzZtzinfosr r skipped_tokensreplrI rL ZcyearZcmonthZcdayretZtzdatar r r r r s\ ?
z parser.parsec @ s& e Zd Zddddddddd d
d g Zd S )
zparser._resultr r r r r r r r r r r N)r rA rB rG r r r r _resulti s r c C st
|rd}| j }|dkr |j}|dkr*|j}| j }tj|}d } t }
yt|} d!} t|}
d} xt||
k ry|| }t |}W n t
k
r d}Y nX |dk rt|| }|d7 }t| dkrH|d"krH|j dkrH||
ks || dkrH|j || dkrH||d }t
|dd |_ |dkrt
|dd |_qf|d kst|d kr||d jd
d kr||d }| r||d jd
d#kr| j|dd | j|dd | j|dd n>> from dateutil.parser import parse
>>> parse("Today is January 1, 2047 at 8:21:00AM", fuzzy_with_tokens=True)
(datetime.datetime(2047, 1, 1, 8, 21), (u'Today is ', u' ', u'at '))
TNr% r r r : r" r
r! < rT rU FzNo hour specified with zAM or PM flag.zInvalid hour specified for z12-hour clock. c S s g | ]}|t jkr|qS r )stringascii_uppercase)rN xr r r r s z!parser._parse..+i ()c S s g | ]}|t jkr|qS r )r r )rN r r r r r s r' )r% r r' )r r r )rT rU r" r' )NNr' )NNr' )rT rU z%No hour specified with AM or PM flag.z)Invalid hour specified for 12-hour clock.)r rT )r rT )r rT r' )r' r )NN)NN)NN)NN)'r r r r r
r0 r< r r- floatr r r r r findr, _parsemsr r r r AssertionErrorr r r strr _skip_tokenr r r r r r r
IndexErrorr r ) r r r r Zfuzzyr r r r5 last_skipped_token_ir Zymdr len_lr Z
value_reprrL len_lir> idxZnewidxZ
sec_remaindersepZ val_is_ampmsignalr r r r r r r n s )
$
,
&
$$
2
4 &
.&
z
parser._parsec C s8 ||d kr"| d || 7 < n| j || |}|S )Nr r' )r, )r r r r5 r r r r - s
zparser._skip_token)N)NFN)NNFF)
r rA rB r r rF r r r r r r r r r s
Ar c K s( |rt |j| f|S tj| f|S dS )a)
Parse a string in one of the supported formats, using the
``parserinfo`` parameters.
:param timestr:
A string containing a date/time stamp.
:param parserinfo:
A :class:`parserinfo` object containing parameters for the parser.
If ``None``, the default arguments to the :class:`parserinfo`
constructor are used.
The ``**kwargs`` parameter takes the following keyword arguments:
:param default:
The default datetime object, if this is a datetime object and not
``None``, elements specified in ``timestr`` replace elements in the
default object.
:param ignoretz:
If set ``True``, time zones in parsed strings are ignored and a naive
:class:`datetime` object is returned.
:param tzinfos:
Additional time zone names / aliases which may be present in the
string. This argument maps time zone names (and optionally offsets
from those time zones) to time zones. This parameter can be a
dictionary with timezone aliases mapping time zone names to time
zones or a function taking two parameters (``tzname`` and
``tzoffset``) and returning a time zone.
The timezones to which the names are mapped can be an integer
offset from UTC in minutes or a :class:`tzinfo` object.
.. doctest::
:options: +NORMALIZE_WHITESPACE
>>> from dateutil.parser import parse
>>> from dateutil.tz import gettz
>>> tzinfos = {"BRST": -10800, "CST": gettz("America/Chicago")}
>>> parse("2012-01-19 17:21:00 BRST", tzinfos=tzinfos)
datetime.datetime(2012, 1, 19, 17, 21, tzinfo=tzoffset(u'BRST', -10800))
>>> parse("2012-01-19 17:21:00 CST", tzinfos=tzinfos)
datetime.datetime(2012, 1, 19, 17, 21,
tzinfo=tzfile('/usr/share/zoneinfo/America/Chicago'))
This parameter is ignored if ``ignoretz`` is set.
:param dayfirst:
Whether to interpret the first value in an ambiguous 3-integer date
(e.g. 01/05/09) as the day (``True``) or month (``False``). If
``yearfirst`` is set to ``True``, this distinguishes between YDM and
YMD. If set to ``None``, this value is retrieved from the current
:class:`parserinfo` object (which itself defaults to ``False``).
:param yearfirst:
Whether to interpret the first value in an ambiguous 3-integer date
(e.g. 01/05/09) as the year. If ``True``, the first number is taken to
be the year, otherwise the last number is taken to be the year. If
this is set to ``None``, the value is retrieved from the current
:class:`parserinfo` object (which itself defaults to ``False``).
:param fuzzy:
Whether to allow fuzzy parsing, allowing for string like "Today is
January 1, 2047 at 8:21:00AM".
:param fuzzy_with_tokens:
If ``True``, ``fuzzy`` is automatically set to True, and the parser
will return a tuple where the first element is the parsed
:class:`datetime.datetime` datetimestamp and the second element is
a tuple containing the portions of the string which were ignored:
.. doctest::
>>> from dateutil.parser import parse
>>> parse("Today is January 1, 2047 at 8:21:00AM", fuzzy_with_tokens=True)
(datetime.datetime(2047, 1, 1, 8, 21), (u'Today is ', u' ', u'at '))
:return:
Returns a :class:`datetime.datetime` object or, if the
``fuzzy_with_tokens`` option is ``True``, returns a tuple, the
first element being a :class:`datetime.datetime` object, the second
a tuple containing the fuzzy tokens.
:raises ValueError:
Raised for invalid or unknown string format, if the provided
:class:`tzinfo` is not in a valid format, or if an invalid date
would be created.
:raises OverflowError:
Raised if the parsed date exceeds the largest valid C integer on
your system.
N)r r
DEFAULTPARSER)r r r r r r r < s _c @ s$ e Zd ZG dd deZdd ZdS ) _tzparserc @ s< e Zd ZddddddgZG dd deZd d
Zd d Zd
S )z_tzparser._resultstdabbr stdoffsetdstabbr dstoffsetstartendc @ s e Zd ZdddddddgZdS ) z_tzparser._result._attrr weekr ydayjydayr r N)r rA rB rG r r r r _attr s r c C s
| j dS )N )rM )r r r r rR s z_tzparser._result.__repr__c C s" t j| | j | _| j | _d S )N)rF r r r r )r r r r r s
z_tzparser._result.__init__N)r rA rB rG rF r rR r r r r r r s
r c C sZ | j }tj|}y$t|}d}x||k r|}x(||k r\dd || D r\|d7 }q6W ||kr|jsd}dj||| |_nd}dj||| |_|}||k o|| d ks|| d d
kr|| d k rd || dk }|d7 }nd }t|| } | d krJt||t|| d d d
t|| d d d | n|d |k r||d dkrt||t|| d
t||d d | |d 7 }n4| d krt||t|| d d d
| nd S |d7 }|jrP q&P q&W ||k rBx*t ||D ] }|| dkrd||< qW || dks:t
|d7 }||krPnd|j d kojdkn rdd ||d D rx|j |j
fD ]}
t|| |
_|d 7 }|| d krt||d d! } |d7 }n t|| } |d 7 }| r| |
_t|| d d |
_nt|| |
_|d 7 }t|| |
_|d 7 }qW ||k r6|| d"kr|d$|| dk }|d7 }nd}|jt|| | |_n|j dd kr6||d j dd kr6dd ||d D r6xF|j |j
fD ]4}
|| dkr|d7 }t|| |
_n|| dkr|d7 }t|| |
_|d7 }|| d%ksXt
|d7 }t|| |
_|
jdkrd&|
_|d7 }|| d'kst
|d7 }t|| d d |
_nt|| d |
_|d7 }||k r|| dkr|d7 }t|| } | d kr>t|| d d d
t|| d d d |
_n|d |k r||d dkrt|| d
t||d d |
_|d 7 }|d |k r||d dkr|d 7 }|
jt|| 7 _n*| d krt|| d d d
|
_nd S |d7 }||ks|| dkst
|d7 }qW ||ks6t
W n ttt
fk
rT d S X |S )(Nr c S s g | ]}|d kr|qS )z0123456789:,-+r )rN r r r r r s z#_tzparser.parse..r r r
r r rT
0123456789r r% i r r rS r$ r c S s* g | ]"}|d kr|D ]}|dkr|qqS )r$ r r )rN r yr r r r s
rU c
S s* g | ]"}|dkr|D ]}|dkr|qqS ) r$ rU JMr" rT r r )r$ rU r r r" rT r r )rN r r r r r r s r r r" r )r rT )r rT r' )r r' r' r' )rT r r' )r' r )rT r" r' )rT r" )r r
r0 r- r rK r rH r ranger r. r r r r r r r r r r r
r r ) r r r r5 r r jZoffattrr r r rL r r r r s
" *
"
(
4 &
z_tzparser.parseN)r rA rB rF r r r r r r r s r c C s
t j| S )N)DEFAULTTZPARSERr )r r r r _parsetzQ s r c C sF d| krt | dfS | jd\}}t |t |jdddd fS dS )z9Parse a I[.F] seconds value into (seconds, microseconds).r" r r r N)r r0 ljust)rL r fr r r r U s r )N)!r Z
__future__r r r r r rC ior Zcalendarr Zsixr r r r
r r
__all__objectr
rF r r< r r r r r r r r r r r r s< # o X
e .