""" This module helps you working with different kinds of text based star catalogs. To adapt the mechanism to your own catlog, create a class extending Catalog() and overwrite the fields and functions as needed. """ import numpy class ParserError(ValueError): pass class Catalog(): def __init__(self, catfile): """ Class with basic When extending the class, change the default settings by overwriting following variables: intro: Number of lines to skip in the beginning of the catalog file. delimiter: Column delimiter strict: If True, the Parser will exit when column descriptions don't match the data. """ super().__init__() self.catfile = catfile self.intro = 0 self.delimiter = ',' self.strict = True # [{'label': str, # 'type': type str|int|float, # 'units': str, # 'explanation': str}] self.columndescriptions = [] def read_column_descriptions(self, descr=None): columns = [] for line in descr.splitlines(): if line.startswith('#'): continue fields = [s.strip() for s in line.split(",")] assert fields[1] in ['str', 'int', 'float'] columns.append({ 'label': fields[0], 'type': eval(fields[1]), 'units': fields[2], 'explanation': fields[3] }) return columns def parse_record(self, linum, line): fields = [s.strip() for s in line.split(self.delimiter)] if self.strict and len(fields) != self._colnum: raise ParserError( "Wrong number of columns in line %d (%d, expected %d)" ""%(linum, len(fields), self._colnum)) parsed = [] for i, (field, type) in enumerate(zip(fields, self._coltypes)): try: if len(field) == 0: if type == str: parsed.append("") else: parsed.append(numpy.nan) else: parsed.append(type(field)) except ValueError as e: if not self.strict: parsed.append(field) else: raise ParserError( "In line %d, field %s: %s" ""%(linum, self.columndescriptions[i]['label'], str(e))) return parsed def records(self, columns=None, filters=None): """ Generator function iterating over the catalog entries. Arguments: columns: list of column labels filters: dict with column labels as keys and these values: if column has type int / float: (min, max) if column has type str: regexp as string or compiled object you can filter for all columns, not only the ones in `columns` """ # save intermediate data for parse_record self._colnum = len(self.columndescriptions) self._coltypes = [col['type'] for col in self.columndescriptions] labels = [col['label'] for col in self.columndescriptions] # convert column labels to indices if columns is None: # list all columns colidxs = list(range(len(self.columndescriptions))) else: colidxs = [labels.index(label) for label in columns] # convert filters to list and compile regexes filterlist = [] if filters is not None: filterlist = [] for label, rule in filters.items(): colidx = labels.index(label) if self._coltypes[colidx] == str and type(rule) == str: rule = re.compile(rule) filterlist.append( (colidx, rule) ) with open(self.catfile, 'r') as f: for i in range(self.intro): next(f) # skip intro lines for linum, line in enumerate(f): fields = self.parse_record(linum, line) for colidx, rule in filterlist: if self._coltypes[colidx] == str: if not rule.fullmatch(fields[colidx]): break else: if not (rule[0] <= fields[colidx] <= rule[1]): break else: yield [fields[i] for i in colidxs] class Hipparcos(Catalog): def __init__(self, catfile): super().__init__(catfile) self.intro = 0 self.delimiter = '|' self.columndescriptions = \ self.read_column_descriptions(DESCRIPTION_HIPPARCOS) def read_column_descriptions(self, descr): columns = [] for line in descr.splitlines()[1:]: fmtidentifier = line[10:15].strip()[0] fmt = {'A': str, 'I': int, 'F': float}[fmtidentifier] columns.append({ 'label': line[23:33].strip(), 'type': fmt, 'units': line[16:22].strip(), 'explanation': line[34:75].strip() }) return columns class HYG(Catalog): def __init__(self, catfile): super().__init__(catfile) self.intro = 1 self.delimiter = ',' self.columndescriptions = self.read_column_descriptions(DESCRIPTION_HYG) DESCRIPTION_HIPPARCOS = \ """Bytes Format Units Label Explanations 1 A1 --- Catalog [H] Catalogue (H=Hipparcos) (H0) 9- 14 I6 --- HIP Identifier (HIP number) (H1) 16 A1 --- Proxy *[HT] Proximity flag (H2) 18- 28 A11 --- RAhms Right ascension in h m s, ICRS (J1991.25) (H3) 30- 40 A11 --- DEdms Declination in deg ' ", ICRS (J1991.25) (H4) 42- 46 F5.2 mag Vmag ? Magnitude in Johnson V (H5) 48 I1 --- VarFlag *[1,3]? Coarse variability flag (H6) 50 A1 --- r_Vmag *[GHT] Source of magnitude (H7) 52- 63 F12.8 deg RAdeg *? alpha, degrees (ICRS, Epoch=J1991.25) (H8) 65- 76 F12.8 deg DEdeg *? delta, degrees (ICRS, Epoch=J1991.25) (H9) 78 A1 --- AstroRef *[*+A-Z] Reference flag for astrometry (H10) 80- 86 F7.2 mas Plx ? Trigonometric parallax (H11) 88- 95 F8.2 mas/yr pmRA *? Proper motion mu_alpha.cos(delta), ICRS(H12) 97-104 F8.2 mas/yr pmDE *? Proper motion mu_delta, ICRS (H13) 106-111 F6.2 mas e_RAdeg *? Standard error in RA*cos(DEdeg) (H14) 113-118 F6.2 mas e_DEdeg *? Standard error in DE (H15) 120-125 F6.2 mas e_Plx ? Standard error in Plx (H16) 127-132 F6.2 mas/yr e_pmRA ? Standard error in pmRA (H17) 134-139 F6.2 mas/yr e_pmDE ? Standard error in pmDE (H18) 141-145 F5.2 --- DE:RA [-1/1]? Correlation, DE/RA*cos(delta) (H19) 147-151 F5.2 --- Plx:RA [-1/1]? Correlation, Plx/RA*cos(delta) (H20) 153-157 F5.2 --- Plx:DE [-1/1]? Correlation, Plx/DE (H21) 159-163 F5.2 --- pmRA:RA [-1/1]? Correlation, pmRA/RA*cos(delta) (H22) 165-169 F5.2 --- pmRA:DE [-1/1]? Correlation, pmRA/DE (H23) 171-175 F5.2 --- pmRA:Plx [-1/1]? Correlation, pmRA/Plx (H24) 177-181 F5.2 --- pmDE:RA [-1/1]? Correlation, pmDE/RA*cos(delta) (H25) 183-187 F5.2 --- pmDE:DE [-1/1]? Correlation, pmDE/DE (H26) 189-193 F5.2 --- pmDE:Plx [-1/1]? Correlation, pmDE/Plx (H27) 195-199 F5.2 --- pmDE:pmRA [-1/1]? Correlation, pmDE/pmRA (H28) 201-203 I3 % F1 ? Percentage of rejected data (H29) 205-209 F5.2 --- F2 *? Goodness-of-fit parameter (H30) 211-216 I6 --- --- HIP number (repetition) (H31) 218-223 F6.3 mag BTmag ? Mean BT magnitude (H32) 225-229 F5.3 mag e_BTmag ? Standard error on BTmag (H33) 231-236 F6.3 mag VTmag ? Mean VT magnitude (H34) 238-242 F5.3 mag e_VTmag ? Standard error on VTmag (H35) 244 A1 --- m_BTmag *[A-Z*-] Reference flag for BT and VTmag (H36) 246-251 F6.3 mag B-V ? Johnson B-V colour (H37) 253-257 F5.3 mag e_B-V ? Standard error on B-V (H38) 259 A1 --- r_B-V [GT] Source of B-V from Ground or Tycho (H39) 261-264 F4.2 mag V-I ? Colour index in Cousins' system (H40) 266-269 F4.2 mag e_V-I ? Standard error on V-I (H41) 271 A1 --- r_V-I *[A-T] Source of V-I (H42) 273 A1 --- CombMag [*] Flag for combined Vmag, B-V, V-I (H43) 275-281 F7.4 mag Hpmag *? Median magnitude in Hipparcos system (H44) 283-288 F6.4 mag e_Hpmag *? Standard error on Hpmag (H45) 290-294 F5.3 mag Hpscat ? Scatter on Hpmag (H46) 296-298 I3 --- o_Hpmag ? Number of observations for Hpmag (H47) 300 A1 --- m_Hpmag *[A-Z*-] Reference flag for Hpmag (H48) 302-306 F5.2 mag Hpmax ? Hpmag at maximum (5th percentile) (H49) 308-312 F5.2 mag HPmin ? Hpmag at minimum (95th percentile) (H50) 314-320 F7.2 d Period ? Variability period (days) (H51) 322 A1 --- HvarType *[CDMPRU]? variability type (H52) 324 A1 --- moreVar *[12] Additional data about variability (H53) 326 A1 --- morePhoto [ABC] Light curve Annex (H54) 328-337 A10 --- CCDM CCDM identifier (H55) 339 A1 --- n_CCDM *[HIM] Historical status flag (H56) 341-342 I2 --- Nsys ? Number of entries with same CCDM (H57) 344-345 I2 --- Ncomp ? Number of components in this entry (H58) 347 A1 --- MultFlag *[CGOVX] Double/Multiple Systems flag (H59) 349 A1 --- Source *[PFILS] Astrometric source flag (H60) 351 A1 --- Qual *[ABCDS] Solution quality (H61) 353-354 A2 --- m_HIP Component identifiers (H62) 356-358 I3 deg theta ? Position angle between components (H63) 360-366 F7.3 arcsec rho ? Angular separation between components (H64) 368-372 F5.3 arcsec e_rho ? Standard error on rho (H65) 374-378 F5.2 mag dHp ? Magnitude difference of components (H66) 380-383 F4.2 mag e_dHp ? Standard error on dHp (H67) 385 A1 --- Survey [S] Flag indicating a Survey Star (H68) 387 A1 --- Chart *[DG] Identification Chart (H69) 389 A1 --- Notes *[DGPWXYZ] Existence of notes (H70) 391-396 I6 --- HD [1/359083]? HD number III/135 (H71) 398-407 A10 --- BD Bonner DM I/119, I/122 (H72) 409-418 A10 --- CoD Cordoba Durchmusterung (DM) I/114 (H73) 420-429 A10 --- CPD Cape Photographic DM I/108 (H74) 431-434 F4.2 mag (V-I)red V-I used for reductions (H75) 436-447 A12 --- SpType Spectral type (H76) 449 A1 --- r_SpType *[1234GKSX]? Source of spectral type (H77) """ DESCRIPTION_HYG = """ # https://github.com/astronexus/HYG-Database # Label,Type,Units,Explanation id,int,,database primary key hip,int,,ID in Hipparcos catalog hd,int,,ID in Henry Draper catalog hr,int,,ID in Harvard Revised catalog and Yale Bright Star Catalog gl,str,,ID in third edition of Gliese Catalog of Nearby Stars bf,str,,Bayer / Flamsteed designation proper,str,,Common name ra,float,deg,J2000.0 dec,float,deg,J2000.0 dist,float,pc, pmra,float,milliarcseconds per year,proper motion pmdec,float,milliarcseconds per year,proper motion rv,float,mag,radial velocity mag,float,mag,apparent visual magnitude absmag,float,mag,absolute visual magnitude spect,str,,spectral type ci,float,,color index x,float,pc, y,float,pc, z,float,pc, vx,float,pc/yr, vy,float,pc/yr, vz,float,pc/yr, rarad,float,rad, decrad,float,rad, pmrarad,float,rad/year,proper motion pmdecrad,float,rad/year,proper motion bayer,str,,Bayer designation flam,str,,Flamsteed number con,str,,standard constellation abbreviation comp,int,,ID of companion star comp_primary,int,,ID of primary star base,str,,ID or name for this multi-star system (Gliese stars only) lum,float,Lsol,luminosity var,str,,standard variable star designation var_min,float,mag, var_max,float,mag, """