|  |
| |
This class is an interface for finding all the month files in a tree of data files as described in the specification.
# - - - - - c l a s s B i r d N o t e T r e e
class BirdNoteTree(object):
'''Represents a complete tree of monthly files.
Exports:
BirdNoteTree(txny, rootDir='.'):
[ (txny is a taxonomy as a Txny instance) and
(rootDir is the path name of a data file tree) ->
if rootDir and its subdirectories can be
examined ->
return a new BirdNoteTree representing the data
files rooted in rootDir with names of the form
"YYYY/YYYY-MM.xml"
else -> raise IOError ]
.txny: [ as passed to constructor, read-only ]
.rootDir: [ as passed to constructor, read-only ]
.genMonths(startDate=None, endDate=None, startSeason=None,
endSeason=None):
[ (startDate is an inclusive starting date as a
datetime.date, or None for no starting cutoff) and
(endDate is an inclusive ending date as a
datetime.date or None for no ending cutoff) and
(startSeason is an inclusive starting month and day
as a datetime.date or None for no starting cutoff) and
(endSeason is an inclusive ending month and day
as a datetime.date or None for no ending cutoff) ->
if all data files in self are readable and
valid against self.txny ->
generate a sequence of BirdNoteSet instances
representing files that may contain dates in
the range [startDate,endDate] and days of the
year in the range [startSeason, endSeason] ]
Internals to this class:
State/Invariants:
._monthList:
[ list of months as "YYYY-MM" representing data files
whose names match "YYYY/YYYY-MM.xml", in ascending
order ]
'''
# - - - B i r d N o t e T r e e . _ _ i n i t _ _
def __init__(self, txny, rootDir='.'):
'''Constructor
'''
We don't read every data file at instantiation. We only
find all the file names that look like yearly
directories; see Section 5.2, “YEAR_PAT: Year directory name
pattern”.
#-- 1 --
self.txny = txny
self.rootDir = rootDir
self._monthList = []
#-- 2 --
# [ if rootDir can be read ->
# yyyyList := list of subdirectories of rootDir
# with four-digit names, sorted
# else -> raise IOError ]
yyyyList = sorted([ dirName
for dirName in os.listdir(rootDir)
if YEAR_PAT.match(dirName) ] )
For the regular expression that matches month file names,
see Section 5.3, “YYYY_MM_XML_PAT: Month file name
pattern”.
#-- 3 --
# [ if all subdirectories of self.rootDir whose names are in
# yyyyList can be read ->
# self._monthList +:= the "YYYY-MM" part of the
# names of files in those subdirectories whose names
# match YYYY_MM_XML_PAT
# else -> raise IOError ]
for yyyy in yyyyList:
#-- 3 body --
# [ if subdirectory (yyyy) of self.rootDir can be read ->
# self._monthList +:= the "YYYY-MM" part of
# the names of files in that subdirectory
# whose names match YYYY_MM_XML_PAT
# else -> raise IOError ]
self._findMonths(yyyy)
#-- 4 --
# [ self._monthList := self._monthList sorted into
# ascending order ]
self._monthList.sort()