completor 0.1.2__py3-none-any.whl → 1.0.0__py3-none-any.whl

completor/parse.py

@@ -169,15 +169,15 @@ def complete_records(record: list[str], keyword: str) -> list[str]:
     Returns:
         Completed list of strings.
     """
-    if keyword == Keywords.WSEGVALV:
+    if keyword == Keywords.WELL_SEGMENTS_VALVE:
         return complete_wsegvalv_record(record)
 
     dict_ncolumns = {
-        Keywords.WELSPECS: 17,
-        Keywords.COMPDAT: 14,
-        Keywords.WELSEGS_H: 12,
-        Keywords.WELSEGS: 15,
-        Keywords.COMPSEGS: 11,
+        Keywords.WELL_SPECIFICATION: 17,
+        Keywords.COMPLETION_DATA: 14,
+        Keywords.WELL_SEGMENTS_HEADER: 12,
+        Keywords.WELL_SEGMENTS: 15,
+        Keywords.COMPLETION_SEGMENTS: 11,
     }
     max_column = dict_ncolumns[keyword]
     ncolumn = len(record)
@@ -190,9 +190,10 @@ def complete_records(record: list[str], keyword: str) -> list[str]:
 
 
 def complete_wsegvalv_record(record: list[str]) -> list[str]:
-    """Complete the WSEGVALV record.
+    """Complete the WELL_SEGMENTS_VALVE record.
 
-    Columns DEFAULT_1 - DEFAULT_4, STATE and AC_MAX might not be provided and need to be filled in with default values.
+    Columns PIPE_DIAMETER, ABSOLUTE_PIPE_ROUGHNESS, PIPE_CROSS_SECTION_AREA, FLAG, and MAX_FLOW_CROSS_SECTIONAL_AREA
+    might not be provided and need to be filled in with default values.
 
     Args:
         record: List of strings.
@@ -200,9 +201,9 @@ def complete_wsegvalv_record(record: list[str]) -> list[str]:
     Returns:
         Completed list of strings.
     """
-    WSEGVALV_COLUMNS = 10
-    AC_INDEX = 3
-    DEFAULT_STATE = "OPEN"
+    wsegvalv_columns = 10
+    ac_index = 3
+    default_state = "OPEN"
 
     if len(record) < 8:
         # add defaults
@@ -210,24 +211,24 @@ def complete_wsegvalv_record(record: list[str]) -> list[str]:
 
     if len(record) < 9:
         # append default state
-        record.append(DEFAULT_STATE)
+        record.append(default_state)
 
-    if len(record) < WSEGVALV_COLUMNS:
+    if len(record) < wsegvalv_columns:
         # append default ac_max
-        record.append(record[AC_INDEX])
+        record.append(record[ac_index])
 
-    if len(record) > WSEGVALV_COLUMNS:
-        record = record[:WSEGVALV_COLUMNS]
+    if len(record) > wsegvalv_columns:
+        record = record[:wsegvalv_columns]
 
     return record
 
 
 def read_schedule_keywords(
-    content: list[str], keywords: list[str], optional_keywords: list[str] = []
+    content: list[str], keywords: list[str], optional_keywords: list[str] | None = None
 ) -> tuple[list[ContentCollection], npt.NDArray[np.str_]]:
     """Read schedule keywords or all keywords in table format.
 
-    E.g. WELSPECS, COMPDAT, WELSEGS, COMPSEGS, WSEGVALV.
+    E.g. WELL_SPECIFICATION, COMPLETION_DATA, WELL_SEGMENTS, COMPLETION_SEGMENTS, WELL_SEGMENTS_VALVE.
 
     Args:
         content: List of strings. Lines from the schedule file.
@@ -244,7 +245,8 @@ def read_schedule_keywords(
     content = deepcopy(content)
     used_index = np.asarray([-1])
     collections = []
-    # get the contents correspond to the list_keywords
+    optional_keywords = [] if optional_keywords is None else optional_keywords
+    # get the contents that correspond with the list_keywords
     for keyword in keywords + optional_keywords:
         start_index, end_index = locate_keyword(content, keyword, take_first=False)
         if start_index[0] == end_index[0] and keyword not in optional_keywords:
@@ -254,7 +256,7 @@ def read_schedule_keywords(
             used_index = np.append(used_index, np.arange(start, end + 1))
             keyword_content = [_create_record(content, keyword, irec, start) for irec in range(start + 1, end)]
             collection = ContentCollection(keyword_content, name=keyword)
-            if keyword in [Keywords.WELSEGS, Keywords.COMPSEGS]:
+            if keyword in [Keywords.WELL_SEGMENTS, Keywords.COMPLETION_SEGMENTS]:
                 # remove string characters
                 collection.well = remove_string_characters(keyword_content[0][0])
             collections.append(collection)
@@ -276,58 +278,58 @@ def _create_record(content: list[str], keyword: str, irec: int, start: int) -> l
     record = unpack_records(record)
     # complete records
     record = complete_records(
-        record, Keywords.WELSEGS_H if keyword == Keywords.WELSEGS and irec == start + 1 else keyword
+        record, Keywords.WELL_SEGMENTS_HEADER if keyword == Keywords.WELL_SEGMENTS and irec == start + 1 else keyword
     )
     return record
 
 
 def get_welsegs_table(collections: list[ContentCollection]) -> tuple[pd.DataFrame, pd.DataFrame]:
-    """Return dataframe table of WELSEGS.
+    """Return dataframe table of WELL_SEGMENTS.
 
     Args:
         collections: ContentCollection class.
 
     Returns:
-        header_table - The header of WELSEGS.
-        record_table - The record of WELSEGS.
+        header_table - The header of WELL_SEGMENTS.
+        record_table - The record of WELL_SEGMENTS.
 
     Raises:
-        ValueError: If collection does not contain the 'WELSEGS' keyword.
+        ValueError: If collection does not contain the 'WELL_SEGMENTSWELL_SEGMENTS' keyword.
     """
     header_columns = [
         Headers.WELL,
-        Headers.SEGMENTTVD,
-        Headers.SEGMENTMD,
-        Headers.WBVOLUME,
+        Headers.TRUE_VERTICAL_DEPTH,
+        Headers.MEASURED_DEPTH,
+        Headers.WELLBORE_VOLUME,
         Headers.INFO_TYPE,
-        Headers.PDROPCOMP,
-        Headers.MPMODEL,
-        Headers.ITEM_8,
-        Headers.ITEM_9,
-        Headers.ITEM_10,
-        Headers.ITEM_11,
-        Headers.ITEM_12,
+        Headers.PRESSURE_DROP_COMPLETION,
+        Headers.MULTIPHASE_FLOW_MODEL,
+        Headers.X_COORDINATE_TOP_SEGMENT,
+        Headers.Y_COORDINATE_TOP_SEGMENT,
+        Headers.THERMAL_CONDUCTIVITY_CROSS_SECTIONAL_AREA,
+        Headers.VOLUMETRIC_HEAT_CAPACITY_PIPE_WALL,
+        Headers.THERMAL_CONDUCTIVITY_PIPE_WALL,
     ]
     content_columns = [
         Headers.WELL,
         Headers.TUBING_SEGMENT,
         Headers.TUBING_SEGMENT_2,
-        Headers.TUBINGBRANCH,
+        Headers.TUBING_BRANCH,
         Headers.TUBING_OUTLET,
-        Headers.TUBINGMD,
-        Headers.TUBINGTVD,
+        Headers.TUBING_MEASURED_DEPTH,
+        Headers.TRUE_VERTICAL_DEPTH,
         Headers.TUBING_INNER_DIAMETER,
         Headers.TUBING_ROUGHNESS,
-        Headers.CROSS,
-        Headers.VSEG,
-        Headers.ITEM_11,
-        Headers.ITEM_12,
-        Headers.ITEM_13,
-        Headers.ITEM_14,
-        Headers.ITEM_15,
+        Headers.FLOW_CROSS_SECTIONAL_AREA,
+        Headers.SEGMENT_VOLUME,
+        Headers.X_COORDINATE_LAST_SEGMENT,
+        Headers.Y_COORDINATE_LAST_SEGMENT,
+        Headers.THERMAL_CONDUCTIVITY_CROSS_SECTIONAL_AREA,
+        Headers.VOLUMETRIC_HEAT_CAPACITY_PIPE_WALL,
+        Headers.THERMAL_CONDUCTIVITY_PIPE_WALL,
     ]
     for collection in collections:
-        if collection.name == Keywords.WELSEGS:
+        if collection.name == Keywords.WELL_SEGMENTS:
             header_collection = np.asarray(collection[:1])
             record_collection = np.asarray(collection[1:])
             # add additional well column on the second collection
@@ -346,7 +348,7 @@ def get_welsegs_table(collections: list[ContentCollection]) -> tuple[pd.DataFram
         header_table = pd.DataFrame(header_table, columns=header_columns)
         record_table = pd.DataFrame(record_table, columns=content_columns)
     except NameError as err:
-        raise ValueError("Collection does not contain the 'WELSEGS' keyword") from err
+        raise ValueError(f"Collection does not contain the '{Keywords.WELL_SEGMENTS}' keyword") from err
 
     # replace string component " or ' in the columns
     header_table = remove_string_characters(header_table)
@@ -355,16 +357,16 @@ def get_welsegs_table(collections: list[ContentCollection]) -> tuple[pd.DataFram
 
 
 def get_welspecs_table(collections: list[ContentCollection]) -> pd.DataFrame:
-    """Return dataframe table of WELSPECS.
+    """Return dataframe table of WELL_SPECIFICATION.
 
     Args:
         collections: ContentCollection class.
 
     Returns:
-        WELSPECS table.
+        WELL_SPECIFICATION table.
 
     Raises:
-        ValueError: If collection does not contain the 'WELSPECS' keyword.
+        ValueError: If collection does not contain the 'WELL_SPECIFICATION' keyword.
     """
     columns = [
         Headers.WELL,
@@ -376,18 +378,18 @@ def get_welspecs_table(collections: list[ContentCollection]) -> pd.DataFrame:
         Headers.DR,
         Headers.FLAG,
         Headers.SHUT,
-        Headers.CROSS,
+        Headers.FLOW_CROSS_SECTIONAL_AREA,
         Headers.PRESSURE_TABLE,
-        Headers.DENSCAL,
+        Headers.DENSITY_CALCULATION_TYPE,
         Headers.REGION,
-        Headers.ITEM_14,
-        Headers.ITEM_15,
-        Headers.ITEM_16,
-        Headers.ITEM_17,
+        Headers.RESERVED_HEADER_1,
+        Headers.RESERVED_HEADER_2,
+        Headers.WELL_MODEL_TYPE,
+        Headers.POLYMER_MIXING_TABLE_NUMBER,
     ]
     welspecs_table = None
     for collection in collections:
-        if collection.name == Keywords.WELSPECS:
+        if collection.name == Keywords.WELL_SPECIFICATION:
             the_collection = np.asarray(collection)
             if welspecs_table is None:
                 welspecs_table = np.copy(the_collection)
@@ -395,7 +397,7 @@ def get_welspecs_table(collections: list[ContentCollection]) -> pd.DataFrame:
                 welspecs_table = np.row_stack((welspecs_table, the_collection))
 
     if welspecs_table is None:
-        raise ValueError("Collection does not contain the 'WELSPECS' keyword")
+        raise ValueError(f"Collection does not contain the '{Keywords.WELL_SPECIFICATION}' keyword")
 
     welspecs_table = pd.DataFrame(welspecs_table, columns=columns)
     # replace string component " or ' in the columns
@@ -404,27 +406,27 @@ def get_welspecs_table(collections: list[ContentCollection]) -> pd.DataFrame:
 
 
 def get_compdat_table(collections: list[ContentCollection]) -> pd.DataFrame:
-    """Return dataframe table of COMPDAT.
+    """Return dataframe table of COMPLETION_DATA.
 
     Args:
         collections: ContentCollection class.
 
     Returns:
-        COMPDAT table.
+        COMPLETION_DATA table.
 
     Raises:
-        ValueError: If a collection does not contain the 'COMPDAT' keyword.
+        ValueError: If a collection does not contain the 'COMPLETION_DATA' keyword.
     """
     compdat_table = None
     for collection in collections:
-        if collection.name == Keywords.COMPDAT:
+        if collection.name == Keywords.COMPLETION_DATA:
             the_collection = np.asarray(collection)
             if compdat_table is None:
                 compdat_table = np.copy(the_collection)
             else:
                 compdat_table = np.row_stack((compdat_table, the_collection))
     if compdat_table is None:
-        raise ValueError("Collection does not contain the 'COMPDAT' keyword")
+        raise ValueError(f"Collection does not contain the '{Keywords.COMPLETION_DATA}' keyword")
     compdat_table = pd.DataFrame(
         compdat_table,
         columns=[
@@ -436,35 +438,33 @@ def get_compdat_table(collections: list[ContentCollection]) -> pd.DataFrame:
             Headers.STATUS,
             Headers.SATURATION_FUNCTION_REGION_NUMBERS,
             Headers.CONNECTION_FACTOR,
-            Headers.DIAMETER,
-            Headers.FORAMTION_PERMEABILITY_THICKNESS,
+            Headers.WELL_BORE_DIAMETER,
+            Headers.FORMATION_PERMEABILITY_THICKNESS,
             Headers.SKIN,
-            Headers.DFACT,
+            Headers.D_FACTOR,
             Headers.COMPDAT_DIRECTION,
             Headers.RO,
         ],
     )
-    # replace string component " or ' in the columns
-    compdat_table = remove_string_characters(compdat_table)
-    return compdat_table
+    return remove_string_characters(compdat_table)
 
 
 def get_compsegs_table(collections: list[ContentCollection]) -> pd.DataFrame:
-    """Return data frame table of COMPSEGS.
+    """Return data frame table of COMPLETION_SEGMENTS.
 
     Args:
         collections: ContentCollection class.
 
     Returns:
-        COMPSEGS table.
+        COMPLETION_SEGMENTS table.
 
     Raises:
-        ValueError: If collection does not contain the 'COMPSEGS' keyword.
+        ValueError: If collection does not contain the 'COMPLETION_SEGMENTS' keyword.
 
     """
     compsegs_table = None
     for collection in collections:
-        if collection.name == Keywords.COMPSEGS:
+        if collection.name == Keywords.COMPLETION_SEGMENTS:
             the_collection = np.asarray(collection[1:])
             # add additional well column
             well_column = np.full(the_collection.shape[0], collection.well)
@@ -475,7 +475,7 @@ def get_compsegs_table(collections: list[ContentCollection]) -> pd.DataFrame:
                 compsegs_table = np.row_stack((compsegs_table, the_collection))
 
     if compsegs_table is None:
-        raise ValueError("Collection does not contain the 'COMPSEGS' keyword")
+        raise ValueError(f"Collection does not contain the '{Keywords.COMPLETION_SEGMENTS}' keyword")
 
     compsegs_table = pd.DataFrame(
         compsegs_table,
@@ -489,8 +489,8 @@ def get_compsegs_table(collections: list[ContentCollection]) -> pd.DataFrame:
             Headers.END_MEASURED_DEPTH,
             Headers.COMPSEGS_DIRECTION,
             Headers.ENDGRID,
-            Headers.PERFDEPTH,
-            Headers.THERM,
+            Headers.PERFORATION_DEPTH,
+            Headers.THERMAL_CONTACT_LENGTH,
             Headers.SEGMENT,
         ],
     )
@@ -500,17 +500,30 @@ def get_compsegs_table(collections: list[ContentCollection]) -> pd.DataFrame:
 
 
 def get_wsegvalv_table(collections: list[ContentCollection]) -> pd.DataFrame:
-    """Return a dataframe of WSEGVALV.
+    """Return a dataframe of WELL_SEGMENTS_VALVE.
 
     Args:
         collections: ContentCollection class.
 
     Returns:
-        WSEGVALV table.
+        WELL_SEGMENTS_VALVE table.
     """
-    columns = ["WELL", "SEGMENT", "CD", "AC", "DEFAULT_1", "DEFAULT_2", "DEFAULT_3", "DEFAULT_4", "STATE", "AC_MAX"]
+    columns = [
+        Headers.WELL,
+        Headers.SEGMENT,
+        Headers.FLOW_COEFFICIENT,
+        Headers.FLOW_CROSS_SECTIONAL_AREA,
+        Headers.ADDITIONAL_PIPE_LENGTH_FRICTION_PRESSURE_DROP,
+        Headers.PIPE_DIAMETER,
+        Headers.ABSOLUTE_PIPE_ROUGHNESS,
+        Headers.PIPE_CROSS_SECTION_AREA,
+        Headers.FLAG,
+        Headers.MAX_FLOW_CROSS_SECTIONAL_AREA,
+    ]
 
-    wsegvalv_collections = [np.asarray(collection) for collection in collections if collection.name == "WSEGVALV"]
+    wsegvalv_collections = [
+        np.asarray(collection) for collection in collections if collection.name == Keywords.WELL_SEGMENTS_VALVE
+    ]
     wsegvalv_table = np.vstack(wsegvalv_collections)
 
     if wsegvalv_table.size == 0:
@@ -519,16 +532,16 @@ def get_wsegvalv_table(collections: list[ContentCollection]) -> pd.DataFrame:
     wsegvalv_table = pd.DataFrame(wsegvalv_table, columns=columns)
     wsegvalv_table = wsegvalv_table.astype(
         {
-            "WELL": "string",
-            "SEGMENT": "int",
-            "CD": "float",
-            "AC": "float",
-            "DEFAULT_1": "string",
-            "DEFAULT_2": "string",
-            "DEFAULT_3": "string",
-            "DEFAULT_4": "string",
-            "STATE": "string",
-            "AC_MAX": "float",
+            Headers.WELL: "string",
+            Headers.SEGMENT: "int",
+            Headers.FLOW_COEFFICIENT: "float",
+            Headers.FLOW_CROSS_SECTIONAL_AREA: "float",
+            Headers.ADDITIONAL_PIPE_LENGTH_FRICTION_PRESSURE_DROP: "string",
+            Headers.PIPE_DIAMETER: "string",
+            Headers.ABSOLUTE_PIPE_ROUGHNESS: "string",
+            Headers.PIPE_CROSS_SECTION_AREA: "string",
+            Headers.FLAG: "string",
+            Headers.MAX_FLOW_CROSS_SECTIONAL_AREA: "float",
         }
     )
     return remove_string_characters(wsegvalv_table)
@@ -570,9 +583,7 @@ def remove_string_characters(df: pd.DataFrame | str, columns: list[str] | None =
             iterator = [] if columns is None else columns
         for column in iterator:
             try:
-                df.iloc[:, column] = remove_quotes(df.iloc[:, column].str)
-            except ValueError:
-                df[column] = remove_quotes(df[column].str)
+                df.isetitem(column, remove_quotes(df.iloc[:, column].str))
             except AttributeError:
                 # Some dataframes contains numeric data, which we ignore
                 pass