Finish implementations, docs, tests

snbianco · snbianco · commit 5087451db050 · 2025-07-02T14:30:49.000-04:00
diff --git a/astroquery/mast/missions.py b/astroquery/mast/missions.py
@@ -472,11 +472,21 @@ def filter_products(self, products, *, extension=None, **filters):
         extension : string or array, optional
             Default is None. Filters by file extension(s), matching any specified extensions.
         **filters :
-            Column-based filters to be applied.
+            Column-based filters to apply to the products table.
+
             Each keyword corresponds to a column name in the table, with the argument being one or more
             acceptable values for that column. AND logic is applied between filters, OR logic within
             each filter set.
-            For example: type="science", extension=["fits","jpg"]
+
+            For example:
+                type="science", extension=["fits", "jpg"]
+
+            For columns with numeric data types (int or float), filter values can be expressed
+            in several ways:
+                - A single number: size=100
+                - A range in the form "start..end": size="100..1000"
+                - A comparison operator followed by a number: size=">=1000"
+                - A list of expressions (OR logic): size=[100, "500..1000", ">=1500"]
 
         Returns
         -------
@@ -504,21 +514,20 @@ def filter_products(self, products, *, extension=None, **filters):
                 continue
 
             col_data = products[colname]
-            # If the column is an integer or float, treat differently
-            if col_data.dtype.kind in 'if' and isinstance(vals, str):
+            # If the column is an integer or float, accept numeric filters
+            if col_data.dtype.kind in 'if':
                 try:
                     col_mask = utils.parse_numeric_product_filter(vals)(col_data)
                 except ValueError:
                     warnings.warn(f"Could not parse numeric filter '{vals}' for column '{colname}'.", InputWarning)
                     continue
-            else:
+            else:  # Assume string or list filter
                 if isinstance(vals, str):
                     vals = [vals]
                 col_mask = np.isin(col_data, vals)
 
             filter_mask &= col_mask
 
-        # Return filtered products
         return products[filter_mask]
 
     def download_file(self, uri, *, local_path=None, cache=True, verbose=True):
diff --git a/astroquery/mast/observations.py b/astroquery/mast/observations.py
@@ -545,7 +545,7 @@ def get_product_list_async(self, observations):
 
     def filter_products(self, products, *, mrp_only=False, extension=None, **filters):
         """
-        Takes an `~astropy.table.Table` of MAST observation data products and filters it based on given filters.
+        Filters an `~astropy.table.Table` of data products based on given filters.
 
         Parameters
         ----------
@@ -556,47 +556,67 @@ def filter_products(self, products, *, mrp_only=False, extension=None, **filters
         extension : string or array, optional
             Default None. Option to filter by file extension.
         **filters :
-            Filters to be applied.  Valid filters are all products fields listed
+            Column-based filters to apply to the products table. Valid filters are all products fields listed
             `here <https://masttest.stsci.edu/api/v0/_productsfields.html>`__.
-            The column name is the keyword, with the argument being one or more acceptable values
-            for that parameter.
-            Filter behavior is AND between the filters and OR within a filter set.
-            For example: productType="SCIENCE",extension=["fits","jpg"]
+
+            Each keyword corresponds to a column name in the table, with the argument being one or more
+            acceptable values for that column. AND logic is applied between filters, OR logic within
+            each filter set.
+
+            For example:
+                type="science", extension=["fits", "jpg"]
+
+            For columns with numeric data types (int or float), filter values can be expressed
+            in several ways:
+                - A single number: size=100
+                - A range in the form "start..end": size="100..1000"
+                - A comparison operator followed by a number: size=">=1000"
+                - A list of expressions (OR logic): size=[100, "500..1000", ">=1500"]
 
         Returns
         -------
         response : `~astropy.table.Table`
+            Filtered table of data products.
         """
 
         filter_mask = np.full(len(products), True, dtype=bool)
 
-        # Applying the special filters (mrp_only and extension)
+        # Filter by minimum recommended products (MRP) if specified
         if mrp_only:
             filter_mask &= (products['productGroupDescription'] == "Minimum Recommended Products")
 
+        # Filter by file extension, if provided
         if extension:
-            if isinstance(extension, str):
-                extension = [extension]
-
-            mask = np.full(len(products), False, dtype=bool)
-            for elt in extension:
-                mask |= [False if isinstance(x, np.ma.core.MaskedConstant) else x.endswith(elt)
-                         for x in products["productFilename"]]
-            filter_mask &= mask
-
-        # Applying the rest of the filters
+            extensions = [extension] if isinstance(extension, str) else extension
+            ext_mask = np.array(
+                [not isinstance(x, np.ma.core.MaskedConstant) and any(x.endswith(ext) for ext in extensions)
+                 for x in products["productFilename"]],
+                dtype=bool
+            )
+            filter_mask &= ext_mask
+
+        # Applying column-based filters
         for colname, vals in filters.items():
+            if colname not in products.colnames:
+                warnings.warn(f"Column '{colname}' not found in product table.", InputWarning)
+                continue
 
-            if isinstance(vals, str):
-                vals = [vals]
-
-            mask = np.full(len(products), False, dtype=bool)
-            for elt in vals:
-                mask |= (products[colname] == elt)
-
-            filter_mask &= mask
-
-        return products[np.where(filter_mask)]
+            col_data = products[colname]
+            # If the column is an integer or float, accept numeric filters
+            if col_data.dtype.kind in 'if':
+                try:
+                    col_mask = utils.parse_numeric_product_filter(vals)(col_data)
+                except ValueError:
+                    warnings.warn(f"Could not parse numeric filter '{vals}' for column '{colname}'.", InputWarning)
+                    continue
+            else:  # Assume string or list filter
+                if isinstance(vals, str):
+                    vals = [vals]
+                col_mask = np.isin(col_data, vals)
+
+            filter_mask &= col_mask
+
+        return products[filter_mask]
 
     def download_file(self, uri, *, local_path=None, base_url=None, cache=True, cloud_only=False, verbose=True):
         """
diff --git a/astroquery/mast/tests/test_mast.py b/astroquery/mast/tests/test_mast.py
@@ -371,11 +371,59 @@ def test_missions_filter_products(patch_post):
     assert isinstance(filtered, Table)
     assert all(filtered['category'] == 'CALIBRATED')
 
+    # Filter by extension
+    filtered = mast.MastMissions.filter_products(products,
+                                                 extension='fits')
+    assert len(filtered) > 0
+
     # Filter by non-existing column
     with pytest.warns(InputWarning):
         mast.MastMissions.filter_products(products,
                                           invalid=True)
 
+    # Numeric filtering
+    # Single integer value
+    filtered = mast.MastMissions.filter_products(products,
+                                                 size=11520)
+    assert all(filtered['size'] == 11520)
+
+    # Single string value
+    filtered = mast.MastMissions.filter_products(products,
+                                                 size='11520')
+    assert all(filtered['size'] == 11520)
+
+    # Comparison operators
+    filtered = mast.MastMissions.filter_products(products,
+                                                 size='<15000')
+    assert all(filtered['size'] < 15000)
+
+    filtered = mast.MastMissions.filter_products(products,
+                                                 size='>15000')
+    assert all(filtered['size'] > 15000)
+
+    filtered = mast.MastMissions.filter_products(products,
+                                                 size='>=14400')
+    assert all(filtered['size'] >= 14400)
+
+    filtered = mast.MastMissions.filter_products(products,
+                                                 size='<=14400')
+    assert all(filtered['size'] <= 14400)
+
+    # Range operator
+    filtered = mast.MastMissions.filter_products(products,
+                                                 size='14400..17280')
+    assert all((filtered['size'] >= 14400) & (filtered['size'] <= 17280))
+
+    # List of expressions
+    filtered = mast.MastMissions.filter_products(products,
+                                                 size=[14400, '>20000'])
+    assert all((filtered['size'] == 14400) | (filtered['size'] > 20000))
+
+    with pytest.warns(InputWarning, match="Could not parse numeric filter 'invalid' for column 'size'"):
+        # Invalid filter value
+        mast.MastMissions.filter_products(products,
+                                          size='invalid')
+
 
 def test_missions_download_products(patch_post, tmp_path):
     # Check string input
@@ -670,11 +718,36 @@ def test_observations_get_product_list(patch_post):
 
 def test_observations_filter_products(patch_post):
     products = mast.Observations.get_product_list('2003738726')
-    result = mast.Observations.filter_products(products,
-                                               productType=["SCIENCE"],
-                                               mrp_only=False)
-    assert isinstance(result, Table)
-    assert len(result) == 7
+    filtered = mast.Observations.filter_products(products,
+                                                 productType=["SCIENCE"],
+                                                 mrp_only=False)
+    assert isinstance(filtered, Table)
+    assert len(filtered) == 7
+
+    # Filter for minimum recommended products
+    filtered = mast.Observations.filter_products(products,
+                                                 mrp_only=True)
+    assert all(filtered['productGroupDescription'] == 'Minimum Recommended Products')
+
+    # Filter by extension
+    filtered = mast.Observations.filter_products(products,
+                                                 extension='fits')
+    assert len(filtered) > 0
+
+    # Filter by non-existing column
+    with pytest.warns(InputWarning):
+        mast.Observations.filter_products(products,
+                                          invalid=True)
+
+    # Numeric filtering
+    filtered = mast.Observations.filter_products(products,
+                                                 size='<50000')
+    assert all(filtered['size'] < 50000)
+
+    # Numeric filter that cannot be parsed
+    with pytest.warns(InputWarning, match="Could not parse numeric filter 'invalid' for column 'size'"):
+        filtered = mast.Observations.filter_products(products,
+                                                     size='invalid')
 
 
 def test_observations_download_products(patch_post, tmpdir):
diff --git a/astroquery/mast/utils.py b/astroquery/mast/utils.py
@@ -354,27 +354,42 @@ def parse_numeric_product_filter(val):
 
     Parameters
     ----------
-    val : str
-        The filter value as a string. It can be a single number, a range in the form of "start..end",
-        or a comparison operator followed by a number (e.g., ">=10", "<5", ">100.5", etc.).
+    val : str or list of str
+        The filter value(s). Each entry can be:
+        - A single number (e.g., "100")
+        - A range in the form "start..end" (e.g., "100..200")
+        - A comparison operator followed by a number (e.g., ">=10", "<5", ">100.5")
 
     Returns
     -------
     response : function
         A function that takes a column of a product table and returns a boolean mask indicating
         which rows satisfy the filter condition.
     """
+    # Regular expression to match range patterns
     range_pattern = re.compile(r'[+-]?(\d+(\.\d*)?|\.\d+)\.\.[+-]?(\d+(\.\d*)?|\.\d+)')
-    if val.startswith('>='):
-        return lambda col: col >= float(val[2:])
-    elif val.startswith('<='):
-        return lambda col: col <= float(val[2:])
-    elif val.startswith('>'):
-        return lambda col: col > float(val[1:])
-    elif val.startswith('<'):
-        return lambda col: col < float(val[1:])
-    elif range_pattern.fullmatch(val):
-        start, end = map(float, val.split('..'))
-        return lambda col: (col >= start) & (col <= end)
+
+    def single_condition(cond):
+        """Helper function to create a condition function for a single value."""
+        if isinstance(cond, (int, float)):
+            return lambda col: col == float(cond)
+        if cond.startswith('>='):
+            return lambda col: col >= float(cond[2:])
+        elif cond.startswith('<='):
+            return lambda col: col <= float(cond[2:])
+        elif cond.startswith('>'):
+            return lambda col: col > float(cond[1:])
+        elif cond.startswith('<'):
+            return lambda col: col < float(cond[1:])
+        elif range_pattern.fullmatch(cond):
+            start, end = map(float, cond.split('..'))
+            return lambda col: (col >= start) & (col <= end)
+        else:
+            return lambda col: col == float(cond)
+
+    if isinstance(val, list):
+        # If val is a list, create a condition for each value and combine them with logical OR
+        conditions = [single_condition(v) for v in val]
+        return lambda col: np.logical_or.reduce([cond(col) for cond in conditions])
     else:
-        return lambda col: col == float(val)
+        return single_condition(val)
diff --git a/docs/mast/mast_cut.rst b/docs/mast/mast_cut.rst
@@ -196,6 +196,8 @@ To access sector information for a particular coordinate, object, or moving targ
    -------------- ------ ------ ---
    tess-s0008-1-1      8      1   1
    tess-s0034-1-2     34      1   2
+   tess-s0061-1-2     61      1   2
+   tess-s0088-1-2     88      1   2
 
 Note that because of the delivery cadence of the
 TICA high level science products, later sectors will be available sooner with TICA than with
@@ -242,6 +244,7 @@ The following example requests SPOC cutouts for a moving target.
    tess-s0029-1-4     29      1   4
    tess-s0043-3-3     43      3   3
    tess-s0044-2-4     44      2   4
+   tess-s0092-4-3     92      4   3
 
 Note that the moving targets functionality is not currently available for TICA,
 so the query will always default to SPOC.
diff --git a/docs/mast/mast_missions.rst b/docs/mast/mast_missions.rst
@@ -243,21 +243,27 @@ In many cases, you will not need to download every product that is associated wi
 and any other of the product fields.
 
 The **AND** operation is performed for a list of filters, and the **OR** operation is performed within a filter set. 
-For example, the filter below will return FITS products that are "science" type **and** have a ``file_suffix`` of "ASN" (association
-files) **or** "JIF" (job information files).
+
+For columns with numeric data types (``int`` or ``float``), filter values can be expressed in several ways:
+  - A single number: ``size=100``
+  - A range in the form "start..end": ``size="100..1000"``
+  - A comparison operator followed by a number: ``size=">=1000"``
+  - A list of expressions (OR logic): ``size=[100, "500..1000", ">=1500"]``
+
+The filter below returns FITS products that are "science" type **and** less than or equal to 20,000 bytes in size
+**and** have a ``file_suffix`` of "ASN" (association files) **or** "JIF" (job information files).
 
 .. doctest-remote-data::
    >>> filtered = missions.filter_products(products,
    ...                                     extension='fits',
    ...                                     type='science',
+   ...                                     size='<=20000',        
    ...                                     file_suffix=['ASN', 'JIF'])
    >>> print(filtered)  # doctest: +IGNORE_OUTPUT
          product_key          access  dataset  ...    category     size   type 
    ---------------------------- ------ --------- ... -------------- ----- -------
    JBTAA0010_jbtaa0010_asn.fits PUBLIC JBTAA0010 ...            AUX 11520 science
-   JBTAA0010_jbtaa0010_jif.fits PUBLIC JBTAA0010 ... JITTER/SUPPORT 60480 science
    JBTAA0020_jbtaa0020_asn.fits PUBLIC JBTAA0020 ...            AUX 11520 science
-   JBTAA0020_jbtaa0020_jif.fits PUBLIC JBTAA0020 ... JITTER/SUPPORT 60480 science
 
 Downloading Data Products
 -------------------------
diff --git a/docs/mast/mast_obsquery.rst b/docs/mast/mast_obsquery.rst
