add a local test

whitespace cleanup

pep8 cleanup

pep8 cleanup

escaped character fix.  The previous commit fixed the outstanding pep8 issue but the fix was not recognized

fix import

yay tests pass

more cleanup of the tags

more fixes

fix local tests

Author: keflavich

astroquery/linelists/cdms/core.py

@@ -13,6 +13,7 @@
 from astroquery.exceptions import InvalidQueryError, EmptyResponseError
 
 import re
+import string
 
 __all__ = ['CDMS', 'CDMSClass']
 
@@ -53,7 +54,7 @@ def query_lines_async(self, min_frequency, max_frequency, *,
             Identifiers of the molecules to search for. If this parameter
             is not provided the search will match any species. Default is 'All'.
             Note that if the molecule name contains parentheses, they must be
-            escaped.  For exmaple, 'H2C(CN)2' must be specified as 'H2C\(CN\)2'.
+            escaped.  For exmaple, 'H2C(CN)2' must be specified as 'H2C\\(CN\\)2'.
 
         temperature_for_intensity : float
             The temperature to use when computing the intensity Smu^2.  Set
@@ -198,12 +199,14 @@ def _parse_result(self, response, verbose=False):
 
         ELO:   Lower state energy in cm^{-1} relative to the ground state.
         GUP:   Upper state degeneracy.
-        TAG:   Species tag or molecular identifier.
-            A negative value flags that the line frequency has
-            been measured in the laboratory.  The absolute value of TAG is then the
-            species tag and ERR is the reported experimental error.  The three most
-            significant digits of the species tag are coded as the mass number of
-            the species.
+        MOLWT: The first half of the molecular weight tag, which is the mass in atomic
+               mass units (Daltons).
+        TAG:   Species tag or molecular identifier.  This only includes the
+               last 3 digits of the CDMS tag
+
+        A negative value of MOLWT flags that the line frequency has been
+        measured in the laboratory.  We record this boolean in the 'Lab'
+        column.  ERR is the reported experimental error.
 
         QNFMT: Identifies the format of the quantum numbers
         Ju/Ku/vu and Jl/Kl/vl are the upper/lower QNs
@@ -226,15 +229,21 @@ def _parse_result(self, response, verbose=False):
                   'DR': 36,
                   'ELO': 38,
                   'GUP': 48,
-                  'TAG': 51,
+                  'MOLWT': 51,
+                  'TAG': 54,
                   'QNFMT': 58,
                   'Ju': 61,
                   'Ku': 63,
                   'vu': 65,
-                  'Jl': 67,
-                  'Kl': 69,
-                  'vl': 71,
-                  'F': 73,
+                  'F1u': 67,
+                  'F2u': 69,
+                  'F3u': 71,
+                  'Jl': 73,
+                  'Kl': 75,
+                  'vl': 77,
+                  'F1l': 79,
+                  'F2l': 81,
+                  'F3l': 83,
                   'name': 89}
 
         result = ascii.read(text, header_start=None, data_start=0,
@@ -243,9 +252,23 @@ def _parse_result(self, response, verbose=False):
                             col_starts=list(starts.values()),
                             format='fixed_width', fast_reader=False)
 
+
         result['FREQ'].unit = u.MHz
         result['ERR'].unit = u.MHz
 
+        result['Lab'] = result['MOLWT'] < 0
+        result['MOLWT'] = np.abs(result['MOLWT'])
+        result['MOLWT'].unit = u.Da
+
+        for suf in 'ul':
+            for qn in ('J', 'v', 'K', 'F1', 'F2', 'F3'):
+                qnind = qn+suf
+                if result[qnind].dtype != int:
+                    intcol = np.array(list(map(parse_letternumber, result[qnind])),
+                                      dtype=int)
+                    result[qnind] = intcol
+
+
         # if there is a crash at this step, something went wrong with the query
         # and the _last_query_temperature was not set.  This shouldn't ever
         # happen, but, well, I anticipate it will.
@@ -314,6 +337,24 @@ def tryfloat(x):
 CDMS = CDMSClass()
 
 
+def parse_letternumber(st):
+    """
+    Parse CDMS's two-letter QNs
+
+    Very Important:
+    Exactly two characters are available for each quantum number. Therefore, half
+    integer quanta are rounded up ! In addition, capital letters are used to
+    indicate quantum numbers larger than 99. E. g. A0 is 100, Z9 is 359. Small
+    types are used to signal corresponding negative quantum numbers.
+    """
+    asc = string.ascii_lowercase
+    ASC = string.ascii_uppercase
+    newst = ''.join(['-' + str(asc.index(x)+10) if x in asc else
+                     str(ASC.index(x)+10) if x in ASC else
+                     x for x in st])
+    return int(newst)
+
+
 class Lookuptable(dict):
 
     def find(self, st, flags):

astroquery/linelists/cdms/tests/data/HC7S.data

@@ -0,0 +1,16 @@
+<!DOCTYPE html
+	PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+	 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml" lang="en-US" xml:lang="en-US">
+<head>
+<title>Untitled Document</title>
+<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
+</head>
+<body>
+<pre>
+  100694.0650     0.4909    -3.9202 2  210.7681255 117501 224C6-1C7C7    C5 1C6C6        HC7S
+  100694.0675     0.4909    -3.9237 2  210.7682253 117501 224C6-1C7C6    C5 1C6C5        HC7S
+  100696.6906     0.4909    -3.9202 2  210.7790255 117501 224C6 1C7C7    C5-1C6C6        HC7S
+  100696.6933     0.4909    -3.9237 2  210.7789253 117501 224C6 1C7C6    C5-1C6C5        HC7S
+  100755.6075     0.4921    -4.0157 2  255.1740253 117501 224C7-1C7C6    C6 1C6C5        HC7S
+</pre></body></html>

astroquery/linelists/cdms/tests/test_cdms.py

@@ -4,8 +4,11 @@
 
 from astropy import units as u
 from astropy.table import Table
-from astroquery.linelists.cdms import CDMS
+from astroquery.linelists.cdms.core import CDMS, parse_letternumber
 
+colname_set = set(['FREQ', 'ERR', 'LGINT', 'DR', 'ELO', 'GUP', 'TAG', 'QNFMT',
+                   'Ju', 'Jl', "vu", "F1u", "F2u", "F3u", "vl", "Ku", "Kl",
+                   "F1l", "F2l", "F3l", "name", "MOLWT", "Lab"])
 
 def data_path(filename):
 
@@ -57,9 +60,54 @@ def test_query():
     tbl = CDMS._parse_result(response)
     assert isinstance(tbl, Table)
     assert len(tbl) == 8
-    assert set(tbl.keys()) == set(['FREQ', 'ERR', 'LGINT', 'DR', 'ELO', 'GUP',
-                                   'TAG', 'QNFMT', 'Ju', 'Jl', "vu", "vl", "Ku", "Kl", "F", "name"])
+    assert set(tbl.keys()) == colname_set
 
     assert tbl['FREQ'][0] == 115271.2018
     assert tbl['ERR'][0] == .0005
     assert tbl['LGINT'][0] == -7.1425
+
+
+def test_parseletternumber():
+    """
+    Very Important:
+    Exactly two characters are available for each quantum number. Therefore, half
+    integer quanta are rounded up ! In addition, capital letters are used to
+    indicate quantum numbers larger than 99. E. g. A0 is 100, Z9 is 359. Small
+    types are used to signal corresponding negative quantum numbers.
+    """
+
+    # examples from the docs
+    assert parse_letternumber("A0") == 100
+    assert parse_letternumber("Z9") == 359
+
+    # inferred?
+    assert parse_letternumber("z9") == -359
+    assert parse_letternumber("ZZ") == 3535
+
+
+def test_hc7s():
+    """
+    Test for a very complicated molecule
+
+    CDMS.query_lines_async(100*u.GHz, 100.755608*u.GHz, molecule='HC7S', parse_name_locally=True)
+    """
+
+    response = MockResponseSpec('HC7S.data')
+    tbl = CDMS._parse_result(response)
+    assert isinstance(tbl, Table)
+    assert len(tbl) == 5
+    assert set(tbl.keys()) == colname_set
+
+    assert tbl['FREQ'][0] == 100694.065
+    assert tbl['ERR'][0] == 0.4909
+    assert tbl['LGINT'][0] == -3.9202
+    assert tbl['MOLWT'][0] == 117
+
+    assert tbl['Ju'][0] == 126
+    assert tbl['Jl'][0] == 125
+    assert tbl['vu'][0] == 127
+    assert tbl['vl'][0] == 126
+    assert tbl['Ku'][0] == -1
+    assert tbl['Kl'][0] == 1
+    assert tbl['F1u'][0] == 127
+    assert tbl['F1l'][0] == 126

astroquery/linelists/cdms/tests/test_cdms_remote.py

@@ -1,4 +1,5 @@
 import pytest
+import numpy as np
 from astropy import units as u
 from astropy.table import Table
 
@@ -57,4 +58,18 @@ def test_remote_regex():
 
 @pytest.mark.remote_data
 def test_2375():
-    pass
+    """
+    Regression test for 2375
+    """
+    tbl = CDMS.query_lines(232567.224454 * u.MHz, 234435.809432 * u.MHz, molecule='H2C(CN)2', parse_name_locally=True)
+
+    assert len(tbl) == 49
+
+    MC = np.ma.core.MaskedConstant()
+
+    for col, val in zip(tbl[0].colnames,
+                        (232588.7246, 0.2828, -4.1005, 3, '293.85404', 45, 66, 506, 303, 44, 14, 30, MC, MC, MC, 45, 13, 33, MC, MC, MC, 'H2C(CN)2', False)):
+        if val is MC:
+            assert tbl[0][col].mask
+        else:
+            assert tbl[0][col] == val