Merge pull request #189 from kinverarity1/issue-17-comma-decimal-mark

Automatically recognise commas as decimal marks

lasio/defaults.py

@@ -61,10 +61,11 @@ def get_default_items():
     }
 
 READ_POLICIES = {
-    'default': ['run-on(-)', 'run-on(.)', 'run-on(NaN.)'],
+    'default': ['comma-decimal-mark', 'run-on(-)', 'run-on(.)', 'run-on(NaN.)'],
     }
 
 READ_SUBS = {
+    'comma-decimal-mark': [(re.compile(r'(\d),(\d)'), r'\1.\2'), ],
     'run-on(-)': [(re.compile(r'(\d)-(\d)'), r'\1 -\2'), ], 
     'run-on(.)': [(re.compile(r'-?\d*\.\d*\.\d*'), ' NaN NaN '), ],
     'run-on(NaN.)': [(re.compile(r'NaN[\.-]\d+'), ' NaN NaN '), ],

lasio/reader.py

@@ -528,6 +528,14 @@ def num(self, x, default=None):
         '''
         if default is None:
             default = x
+
+        # in case it is a string.
+        try:
+            pattern, sub = defaults.READ_SUBS['comma-decimal-mark'][0]
+            x = re.sub(pattern, sub, x)
+        except:
+            pass
+
         try:
             return np.int(x)
         except:

tests/examples/comma_decimal_mark.las

@@ -0,0 +1,46 @@
+~VERSION INFORMATION
+ VERS.                  1.2:   CWLS LOG ASCII STANDARD -VERSION 1.2
+ WRAP.                  NO:   ONE LINE PER DEPTH STEP
+~WELL INFORMATION BLOCK
+#MNEM.UNIT       DATA TYPE    INFORMATION
+#---------    -------------   ------------------------------
+ STRT.M        1670.000000:
+ STOP.M        1660.000000:
+ STEP.M            -0.1250:
+ NULL.           -999.2500:
+ COMP.             COMPANY:   # ANY OIL COMPANY LTD.
+ WELL.                WELL:   ANY ET AL OIL WELL #12
+ FLD .               FIELD:   EDAM
+ LOC .            LOCATION:   A9-16-49-20W3M
+ PROV.            PROVINCE:   SASKATCHEWAN
+ SRVC.     SERVICE COMPANY:   ANY LOGGING COMPANY LTD.
+ DATE.            LOG DATE:   25-DEC-1988
+ UWI .      UNIQUE WELL ID:   100091604920W300
+~CURVE INFORMATION
+#MNEM.UNIT      API CODE      CURVE DESCRIPTION
+#---------    -------------   ------------------------------
+ DEPT.M                      :  1  DEPTH
+ DT  .US/M     		     :  2  SONIC TRANSIT TIME
+ RHOB.K/M3                   :  3  BULK DENSITY
+ NPHI.V/V                    :  4   NEUTRON POROSITY
+ SFLU.OHMM                   :  5  RXO RESISTIVITY
+ SFLA.OHMM                   :  6  SHALLOW RESISTIVITY
+ ILM .OHMM                   :  7  MEDIUM RESISTIVITY
+ ILD .OHMM                   :  8  DEEP RESISTIVITY
+~PARAMETER INFORMATION
+#MNEM.UNIT        VALUE       DESCRIPTION
+#---------    -------------   ------------------------------
+ BHT .DEGC         35.5000:   BOTTOM HOLE TEMPERATURE
+ BS  .MM          200.0000:   BIT SIZE
+ FD  .K/M3       1000.0000:   FLUID DENSITY
+ MATR.              0.0000:   NEUTRON MATRIX(0=LIME,1=SAND,2=DOLO)
+ MDEN.           2710,1000:   LOGGING MATRIX DENSITY
+ RMF .OHMM          0.2160:   MUD FILTRATE RESISTIVITY
+ DFD .K/M3       1525.0000:   DRILL FLUID DENSITY
+~Other
+     Note: The logging tools became stuck at 625 meters causing the data
+	   between 625 meters and 615 meters to be invalid.
+~A  DEPTH     DT       RHOB     NPHI     SFLU     SFLA      ILM      ILD
+1670.000   123.450 2550.000    0.450  123.450  123.450  110.200  105.600
+1669.875   123.450 2550.000    0.450  123,420  123.450  110.200  105.600
+1669.750   123.450 2550.000    0.450  123.450  123.450  110.200  105.600

tests/test_read.py

@@ -165,3 +165,11 @@ def test_barebones_missing_all_sections():
 def test_not_a_las_file():
     with pytest.raises(KeyError):
         las = read(egfn('not_a_las_file.las'))
+
+def test_comma_decimal_mark_data():
+    las = read(egfn('comma_decimal_mark.las'))
+    assert las['SFLU'][1] == 123.42
+
+def test_comma_decimal_mark_params():
+    las = read(egfn('comma_decimal_mark.las'))
+    assert las.params['MDEN'].value == 2710.1