don't even try heavily penalized searches

[nominatim.git] / nominatim / api / logging.py

diff --git a/nominatim/api/logging.py b/nominatim/api/logging.py
index 6c8b1b388224f8a787977b15e7c2e2fce5aaab03..30999a3f31282a085520baabf1a6b308f9d6ed7b 100644 (file)
--- a/nominatim/api/logging.py
+++ b/nominatim/api/logging.py
@@ -7,11 +7,13 @@
 """
 Functions for specialised logging with HTML output.
 """
 """
 Functions for specialised logging with HTML output.
 """

-from typing import Any, Iterator, Optional, List, Tuple, cast
+from typing import Any, Iterator, Optional, List, Tuple, cast, Union, Mapping, Sequence

 from contextvars import ContextVar
 import datetime as dt
 import textwrap
 import io
 from contextvars import ContextVar
 import datetime as dt
 import textwrap
 import io

+import re
+import html

 
 import sqlalchemy as sa
 from sqlalchemy.ext.asyncio import AsyncConnection
 
 import sqlalchemy as sa
 from sqlalchemy.ext.asyncio import AsyncConnection


@@ -74,23 +76,57 @@ class BaseLogger:
         """
 
 
         """
 
 

-    def sql(self, conn: AsyncConnection, statement: 'sa.Executable') -> None:
+    def sql(self, conn: AsyncConnection, statement: 'sa.Executable',
+            params: Union[Mapping[str, Any], Sequence[Mapping[str, Any]], None]) -> None:

         """ Print the SQL for the given statement.
         """
 
         """ Print the SQL for the given statement.
         """
 

-    def format_sql(self, conn: AsyncConnection, statement: 'sa.Executable') -> str:
-        """ Return the comiled version of the statement.
+    def format_sql(self, conn: AsyncConnection, statement: 'sa.Executable',
+                   extra_params: Union[Mapping[str, Any],
+                                 Sequence[Mapping[str, Any]], None]) -> str:
+        """ Return the compiled version of the statement.

         """
         """

-        try:
-            return str(cast('sa.ClauseElement', statement)
-                         .compile(conn.sync_engine, compile_kwargs={"literal_binds": True}))
-        except sa.exc.CompileError:
-            pass
-        except NotImplementedError:
-            pass
-
-        return str(cast('sa.ClauseElement', statement).compile(conn.sync_engine))
-
+        compiled = cast('sa.ClauseElement', statement).compile(conn.sync_engine)
+
+        params = dict(compiled.params)
+        if isinstance(extra_params, Mapping):
+            for k, v in extra_params.items():
+                if hasattr(v, 'to_wkt'):
+                    params[k] = v.to_wkt()
+                elif isinstance(v, (int, float)):
+                    params[k] = v
+                else:
+                    params[k] = str(v)
+        elif isinstance(extra_params, Sequence) and extra_params:
+            for k in extra_params[0]:
+                params[k] = f':{k}'
+
+        sqlstr = str(compiled)
+
+        if conn.dialect.name == 'postgresql':
+            if sa.__version__.startswith('1'):
+                try:
+                    sqlstr = re.sub(r'__\[POSTCOMPILE_[^]]*\]', '%s', sqlstr)
+                    return sqlstr % tuple((repr(params.get(name, None))
+                                          for name in compiled.positiontup)) # type: ignore
+                except TypeError:
+                    return sqlstr
+
+            # Fixes an odd issue with Python 3.7 where percentages are not
+            # quoted correctly.
+            sqlstr = re.sub(r'%(?!\()', '%%', sqlstr)
+            sqlstr = re.sub(r'__\[POSTCOMPILE_([^]]*)\]', r'%(\1)s', sqlstr)
+            return sqlstr % params
+
+        assert conn.dialect.name == 'sqlite'
+
+        # params in positional order
+        pparams = (repr(params.get(name, None)) for name in compiled.positiontup) # type: ignore
+
+        sqlstr = re.sub(r'__\[POSTCOMPILE_([^]]*)\]', '?', sqlstr)
+        sqlstr = re.sub(r"\?", lambda m: next(pparams), sqlstr)
+
+        return sqlstr

 
 class HTMLLogger(BaseLogger):
     """ Logger that formats messages in HTML.
 
 class HTMLLogger(BaseLogger):
     """ Logger that formats messages in HTML.


@@ -183,15 +219,16 @@ class HTMLLogger(BaseLogger):
         self._write(f'</dl><b>TOTAL:</b> {total}</p>')
 
 
         self._write(f'</dl><b>TOTAL:</b> {total}</p>')
 
 

-    def sql(self, conn: AsyncConnection, statement: 'sa.Executable') -> None:
+    def sql(self, conn: AsyncConnection, statement: 'sa.Executable',
+            params: Union[Mapping[str, Any], Sequence[Mapping[str, Any]], None]) -> None:

         self._timestamp()
         self._timestamp()

-        sqlstr = self.format_sql(conn, statement)
+        sqlstr = self.format_sql(conn, statement, params)

         if CODE_HIGHLIGHT:
             sqlstr = highlight(sqlstr, PostgresLexer(),
                                HtmlFormatter(nowrap=True, lineseparator='<br />'))
             self._write(f'<div class="highlight"><code class="lang-sql">{sqlstr}</code></div>')
         else:
         if CODE_HIGHLIGHT:
             sqlstr = highlight(sqlstr, PostgresLexer(),
                                HtmlFormatter(nowrap=True, lineseparator='<br />'))
             self._write(f'<div class="highlight"><code class="lang-sql">{sqlstr}</code></div>')
         else:

-            self._write(f'<code class="lang-sql">{sqlstr}</code>')
+            self._write(f'<code class="lang-sql">{html.escape(sqlstr)}</code>')

 
 
     def _python_var(self, var: Any) -> str:
 
 
     def _python_var(self, var: Any) -> str:


@@ -199,7 +236,7 @@ class HTMLLogger(BaseLogger):
             fmt = highlight(str(var), PythonLexer(), HtmlFormatter(nowrap=True))
             return f'<div class="highlight"><code class="lang-python">{fmt}</code></div>'
 
             fmt = highlight(str(var), PythonLexer(), HtmlFormatter(nowrap=True))
             return f'<div class="highlight"><code class="lang-python">{fmt}</code></div>'
 

-        return f'<code class="lang-python">{str(var)}</code>'
+        return f'<code class="lang-python">{html.escape(str(var))}</code>'

 
 
     def _write(self, text: str) -> None:
 
 
     def _write(self, text: str) -> None:


@@ -215,6 +252,10 @@ class TextLogger(BaseLogger):
         self.buffer = io.StringIO()
 
 
         self.buffer = io.StringIO()
 
 

+    def _timestamp(self) -> None:
+        self._write(f'[{dt.datetime.now()}]\n')
+
+

     def get_buffer(self) -> str:
         return self.buffer.getvalue()
 
     def get_buffer(self) -> str:
         return self.buffer.getvalue()
 


@@ -227,6 +268,7 @@ class TextLogger(BaseLogger):
 
 
     def section(self, heading: str) -> None:
 
 
     def section(self, heading: str) -> None:

+        self._timestamp()

         self._write(f"\n# {heading}\n\n")
 
 
         self._write(f"\n# {heading}\n\n")
 
 


@@ -263,6 +305,7 @@ class TextLogger(BaseLogger):
 
 
     def result_dump(self, heading: str, results: Iterator[Tuple[Any, Any]]) -> None:
 
 
     def result_dump(self, heading: str, results: Iterator[Tuple[Any, Any]]) -> None:

+        self._timestamp()

         self._write(f'{heading}:\n')
         total = 0
         for rank, res in results:
         self._write(f'{heading}:\n')
         total = 0
         for rank, res in results:


@@ -276,8 +319,10 @@ class TextLogger(BaseLogger):
         self._write(f'TOTAL: {total}\n\n')
 
 
         self._write(f'TOTAL: {total}\n\n')
 
 

-    def sql(self, conn: AsyncConnection, statement: 'sa.Executable') -> None:
-        sqlstr = '\n| '.join(textwrap.wrap(self.format_sql(conn, statement), width=78))
+    def sql(self, conn: AsyncConnection, statement: 'sa.Executable',
+            params: Union[Mapping[str, Any], Sequence[Mapping[str, Any]], None]) -> None:
+        self._timestamp()
+        sqlstr = '\n| '.join(textwrap.wrap(self.format_sql(conn, statement, params), width=78))

         self._write(f"| {sqlstr}\n\n")
 
 
         self._write(f"| {sqlstr}\n\n")