sql-blocks 1.25.30011644__py3-none-any.whl → 1.25.32011301__py3-none-any.whl

sql_blocks/sql_blocks.py

@@ -65,6 +65,11 @@ class SQLObject:
     def table_name(self) -> str:
         return self.values[FROM][0].split()[0]
     
+    def set_file_format(self, pattern: str):
+        if '{' not in pattern:
+            pattern = '{}' + pattern
+        self.values[FROM][0] = pattern.format(self.aka())
+
     @property
     def alias(self) -> str:
         if self.__alias:
@@ -366,15 +371,20 @@ class ExpressionField:
 class FieldList:
     separator = ','
 
-    def __init__(self, fields: list=[], class_types = [Field]):
+    def __init__(self, fields: list=[], class_types = [Field], ziped: bool=False):
         if isinstance(fields, str):
             fields = [
                 f.strip() for f in fields.split(self.separator)
             ]
         self.fields = fields
         self.class_types = class_types
+        self.ziped = ziped
 
     def add(self, name: str, main: SQLObject):
+        if self.ziped:  # --- One class per field...
+            for field, class_type in zip(self.fields, self.class_types):
+                class_type.add(field, main)
+            return
         for field in self.fields:
             for class_type in self.class_types:
                 class_type.add(field, main)
@@ -1112,7 +1122,11 @@ class CypherParser(Parser):
         if token in self.TOKEN_METHODS:
             return
         class_list = [Field]
-        if '$' in token:
+        if '*' in token:
+            token = token.replace('*', '')
+            self.queries[-1].key_field = token
+            return
+        elif '$' in token:
             func_name, token = token.split('$')
             if func_name == 'count':
                 if not token:
@@ -1136,10 +1150,13 @@ class CypherParser(Parser):
     def add_foreign_key(self, token: str, pk_field: str=''):
         curr, last = [self.queries[i] for i in (-1, -2)]
         if not pk_field:
-            if not last.values.get(SELECT):
-                raise IndexError(f'Primary Key not found for {last.table_name}.')
-            pk_field = last.values[SELECT][-1].split('.')[-1]
-            last.delete(pk_field, [SELECT], exact=True)
+            if last.key_field:
+                pk_field = last.key_field
+            else:
+                if not last.values.get(SELECT):
+                    raise IndexError(f'Primary Key not found for {last.table_name}.')
+                pk_field = last.values[SELECT][-1].split('.')[-1]
+                last.delete(pk_field, [SELECT], exact=True)
         if '{}' in token:
             foreign_fld = token.format(
                 last.table_name.lower()
@@ -1457,33 +1474,35 @@ class NotSelectIN(SelectIN):
     condition_class = Not
 
 
-class CTE:
+class CTE(Select):
     prefix = ''
 
-    def __init__(self, name: str, query_list: list[Select]):
-        self.name = name
+    def __init__(self, table_name: str, query_list: list[Select]):
+        super().__init__(table_name)
         for query in query_list:
             query.break_lines = False
         self.query_list = query_list
-
-    def format(self, query: Select) -> str:
-        LINE_MAX_SIZE = 50
-        result, line = [], ''
-        for word in str(query).split(' '):
-            if len(line) >= LINE_MAX_SIZE and word in KEYWORD:
-                result.append(line)
-                line = ''
-            line += word + ' '
-        if line:
-            result.append(line)
-        return '\n\t'.join(result)
+        self.break_lines = False
 
     def __str__(self) -> str:
-        return 'WITH {prefix}{name} AS (\n\t{queries}\n)SELECT * FROM {name}'.format(
-            prefix=self.prefix, name=self.name, 
-            queries='\nUNION ALL\n\t'.join(
-                self.format(q) for q in self.query_list
-            )
+        # ---------------------------------------------------------
+        def justify(query: Select) -> str:
+            result, line = [], ''
+            keywords = '|'.join(KEYWORD)
+            for word in re.split(fr'({keywords}|AND|OR|,)', str(query)):
+                if len(line) >= 65:
+                    result.append(line)
+                    line = ''
+                line += word
+            if line:
+                result.append(line)
+            return '\n    '.join(result)
+        # ---------------------------------------------------------
+        return 'WITH {}{} AS (\n    {}\n){}'.format(
+            self.prefix, self.table_name, 
+            '\nUNION ALL\n    '.join(
+                justify(q) for q in self.query_list
+            ), super().__str__()
         )
 
 class Recursive(CTE):
@@ -1491,10 +1510,49 @@ class Recursive(CTE):
 
     def __str__(self) -> str:
         if len(self.query_list) > 1:
-            alias = self.name[0].lower()
-            self.query_list[-1].values[FROM].append(f', {self.name} {alias}')
+            self.query_list[-1].values[FROM].append(
+                f', {self.table_name} {self.alias}')
         return super().__str__()
 
+    @classmethod
+    def create(cls, name: str, pattern: str, formula: str, init_value, format: str=''):
+        SQLObject.ALIAS_FUNC = None
+        def get_field(obj: SQLObject, pos: int) -> str:
+            return obj.values[SELECT][pos].split('.')[-1]
+        t1, t2 = detect(
+            pattern*2, join_queries=False, format=format
+        )
+        pk_field = get_field(t1, 0)
+        foreign_key = ''
+        for num in re.findall(r'\[(\d+)\]', formula):
+            num = int(num)
+            if not foreign_key:
+                foreign_key = get_field(t2, num-1)
+                formula = formula.replace(f'[{num}]', '%')
+            else:
+                formula = formula.replace(f'[{num}]', get_field(t2, num-1))
+        Where.eq(init_value).add(pk_field, t1)
+        Where.formula(formula).add(foreign_key or pk_field, t2)
+        return cls(name, [t1, t2])
+
+    def join(self, pattern: str, fields: list | str, format: str):
+        if isinstance(fields, str):
+            count = len( fields.split(',') )
+        else:
+            count = len(fields)
+        queries = detect(
+            pattern*count, join_queries=False, format=format
+        )
+        FieldList(fields, queries, ziped=True).add('', self)
+        self.break_lines = True
+
+    def counter(self, name: str, start, increment: str='+1'):
+        for i, query in enumerate(self.query_list):
+            if i == 0:
+                Field.add(f'{start} AS {name}', query)
+            else:
+                Field.add(f'({name}{increment}) AS {name}', query)
+
 
 # ----- Rules -----
 
@@ -1612,7 +1670,7 @@ def parser_class(text: str) -> Parser:
     return None
 
 
-def detect(text: str, join_queries: bool = True) -> Select | list[Select]:
+def detect(text: str, join_queries: bool = True, format: str='') -> Select | list[Select]:
     from collections import Counter
     parser = parser_class(text)
     if not parser:
@@ -1623,11 +1681,14 @@ def detect(text: str, join_queries: bool = True) -> Select | list[Select]:
                 continue
             pos = [ f.span() for f in re.finditer(fr'({table})[(]', text) ]
             for begin, end in pos[::-1]:
-                new_name = f'{table}_{count}'  # See set_table (line 45)
+                new_name = f'{table}_{count}'  # See set_table (line 55)
                 Select.EQUIVALENT_NAMES[new_name] = table
                 text = text[:begin] + new_name + '(' + text[end:]
                 count -= 1
     query_list = Select.parse(text, parser)
+    if format:
+        for query in query_list:
+            query.set_file_format(format)
     if not join_queries:
         return query_list
     result = query_list[0]
@@ -1635,3 +1696,4 @@ def detect(text: str, join_queries: bool = True) -> Select | list[Select]:
         result += query
     return result
 
+

{sql_blocks-1.25.30011644.dist-info → sql_blocks-1.25.32011301.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sql_blocks
-Version: 1.25.30011644
+Version: 1.25.32011301
 Summary: Allows you to create objects for parts of SQL query commands. Also to combine these objects by joining them, adding or removing parts...
 Home-page: https://github.com/julio-cascalles/sql_blocks
 Author: Júlio Cascalles
@@ -98,10 +98,7 @@ query = Select('Movie m', title=Field,
         awards=contains("Oscar")
     )
     AND=Options(
-        ..., name=contains(
-            'Chris',
-            Position.StartsWith
-        )
+        ..., name=startswith('Chris')
     )
 ```
 
@@ -175,8 +172,8 @@ FROM
             artist.name as artist_name,
             album.year_recorded
     FROM
-            'sql_blocks/music/data/Album.csv' album
-            ,'sql_blocks/music/data/Singer.csv' artist
+            Album album
+            ,Singer artist
     WHERE
             (album.artist_id = artist.id)
 
@@ -412,7 +409,7 @@ m2 = Select(
     query = Select(
         'Installments i', due_date=Field,  customer=Select(
             'Customer c', id=PrimaryKey,
-            name=contains('Smith', Position.EndsWith)
+            name=endswith('Smith')
         )
     )
     print(query)
@@ -492,6 +489,7 @@ ORDER BY
 * `^` Put the field in the ORDER BY clause
 * `@` Immediately after the table name, it indicates the grouping field.
 * `$` For SQL functions like **avg**$_field_, **sum**$_field_, **count**$_field_...
+* `*` Sets the primary key field.
 
 
 ---
@@ -674,7 +672,7 @@ For example, if your query is going to run on Oracle, do the following:
 
 ### 17 - CTE and Recursive classes
 
-* **_CTE class_**
+* **17.1 - _CTE class_**
 ```
     query = Select(
         'SocialMedia s', post=Count, reaction=Sum, user=GroupBy
@@ -688,7 +686,7 @@ The result is...
     )SELECT * FROM Metrics
 ```
 
-* **_Recursive class_**
+* **17.2 - _Recursive class_**
 ```
 q1 = Select(
     'SocialMedia me', name=[ eq(MY_NAME), Field ]
@@ -701,8 +699,90 @@ print( Recursive('Network', [q1, q2]) )
 The result is...
 ```
 WITH RECURSIVE Network AS (
-        SELECT me.name FROM SocialMedia me WHERE me.name = 'Júlio Cascalles'
+        SELECT me.name FROM SocialMedia me WHERE 
+        me.name = 'Júlio Cascalles'
 UNION ALL
-        SELECT you.name FROM SocialMedia you , Network n WHERE  you.id = n.friend
+        SELECT you.name FROM SocialMedia you , Network n
+        WHERE  you.id = n.friend
 )SELECT * FROM Network
 ```
+
+* **17.2.1 - The `create` method** ... parameters :
+    - name: The name of the CTE
+    - pattern: A cypher script that defines the tables used
+    - formula: The format for `Where.formula` method _(*)_
+    - init_value: The value for the condition in the first table
+    - format (optional): If tables are files or internet hiperlinks, you may especify the extension and/or folder...
+> Example: 
+```
+    R = Recursive.create(
+        'Route R', 'Flyght(departure, arrival)',
+        '[2] = R.[1]',  'JFK',  format='.csv'
+    ) #                  ^^^--- Flyghts from JFK airport
+```
+_...Creates a recursive CTE called Route, using Flyght table, where the recursivity condition is Flyght.arrival equals to Route.departure_
+>> (*) -- Note that [1] and [2] refers to first field and second field. 😉
+
+Result:
+
+    WITH RECURSIVE Route AS (
+            SELECT f1.departure, f1.arrival
+            FROM Flyght.csv f1
+            WHERE f1.departure = 'JFK'
+    UNION ALL
+            SELECT f2.departure, f2.arrival
+            FROM Flyght.csv f2
+            , Route R
+            WHERE  f2.arrival = R.departure
+    )SELECT * FROM Route R
+
+**17.2.2 - The `join` method** 
+
+In the previous example, if you add this code...
+`R.join('Airport(*id,name)', 'departure, arrival', format='.csv')`
+
+...The result would be:
+
+    WITH RECURSIVE Route AS (
+        SELECT f1.departure, f1.arrival
+        FROM Flyght.csv f1
+        WHERE f1.departure = 'JFK'
+    UNION ALL
+        SELECT f2.departure, f2.arrival
+        FROM Flyght.csv f2
+        , Route R
+        WHERE  f2.arrival = R.departure
+    )SELECT
+        a1.name, a2.name
+    FROM
+        Route R
+        JOIN Airport.csv a2 ON (R.arrival = a2.id)
+        JOIN Airport.csv a1 ON (R.departure = a1.id)
+
+
+**17.2.3 - The `counter` method** 
+Adds an increment field in queries inside CTE:
+> Examples:
+* `R.counter('stops', 0)` # -- counter starts with 0 and increment +1
+* `R2.counter('generation', 5, '- 1')` # -- for the code below...
+```
+R2 = Recursive.create(
+    'Ancestors a', 'People(id,name,father,mother,birth)',
+    '(% = a.father OR % = a.mother)', 32630, '.parquet'
+)
+```
+...Results:
+
+    WITH RECURSIVE Ancestors AS (
+        SELECT p1.id, p1.name, p1.father, p1.mother, p1.birth,
+        5 AS generation  /* <<---- Most current generation ------------*/
+        FROM People.parquet p1 WHERE p1.id = 32630
+    UNION ALL
+        SELECT p2.id, p2.name, p2.father, p2.mother, p2.birth,
+        (generation- 1) AS generation /* <<-- Previous generation -----*/
+        FROM People.parquet p2 , Ancestors a WHERE  (p2.id = a.father OR p2.id = a.mother)
+    )SELECT * FROM Ancestors a
+
+
+>> Note: Comments added later.
+---

sql_blocks-1.25.32011301.dist-info/RECORD

@@ -0,0 +1,7 @@
+sql_blocks/__init__.py,sha256=5ItzGCyqqa6kwY8wvF9kapyHsAiWJ7KEXCcC-OtdXKg,37
+sql_blocks/sql_blocks.py,sha256=VW8n2nWu7RREnns8dmYruhlvzGBCA3EeuBKiXCjClmE,56975
+sql_blocks-1.25.32011301.dist-info/LICENSE,sha256=6kbiFSfobTZ7beWiKnHpN902HgBx-Jzgcme0SvKqhKY,1091
+sql_blocks-1.25.32011301.dist-info/METADATA,sha256=g_Yr5mTcquKqG5PM6qSNeWsuZ4wbo88pdZUldp_rt9k,19574
+sql_blocks-1.25.32011301.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+sql_blocks-1.25.32011301.dist-info/top_level.txt,sha256=57AbUvUjYNy4m1EqDaU3WHeP-uyIAfV0n8GAUp1a1YQ,11
+sql_blocks-1.25.32011301.dist-info/RECORD,,

sql_blocks-1.25.30011644.dist-info/RECORD

@@ -1,7 +0,0 @@
-sql_blocks/__init__.py,sha256=5ItzGCyqqa6kwY8wvF9kapyHsAiWJ7KEXCcC-OtdXKg,37
-sql_blocks/sql_blocks.py,sha256=2R4VoSZUHTb1gSZwKjtNfkjxeH8G1dKYuDpuKv-UP7E,54430
-sql_blocks-1.25.30011644.dist-info/LICENSE,sha256=6kbiFSfobTZ7beWiKnHpN902HgBx-Jzgcme0SvKqhKY,1091
-sql_blocks-1.25.30011644.dist-info/METADATA,sha256=2Q1naQygxXqw87DTc70LyLjs8uWK95v0CWu5B9qHLlQ,16884
-sql_blocks-1.25.30011644.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-sql_blocks-1.25.30011644.dist-info/top_level.txt,sha256=57AbUvUjYNy4m1EqDaU3WHeP-uyIAfV0n8GAUp1a1YQ,11
-sql_blocks-1.25.30011644.dist-info/RECORD,,