postcodes: exclude seen places later

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

diff --git a/nominatim/api/logging.py b/nominatim/api/logging.py
index 8d9af10c81aceb57a2117a99ff28491b79c69665..30999a3f31282a085520baabf1a6b308f9d6ed7b 100644 (file)
--- a/nominatim/api/logging.py
+++ b/nominatim/api/logging.py
@@ -12,6 +12,8 @@ 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
@@ -80,21 +82,51 @@ class BaseLogger:
         """
 
     def format_sql(self, conn: AsyncConnection, statement: 'sa.Executable',
-                   extra_params: Union[Mapping[str, Any], Sequence[Mapping[str, Any]], None]) -> str:
-        """ Return the comiled version of the statement.
+                   extra_params: Union[Mapping[str, Any],
+                                 Sequence[Mapping[str, Any]], None]) -> str:
+        """ Return the compiled version of the statement.
         """
         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():
-                params[k] = str(v)
+                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}'
 
-        return str(compiled) % params
+        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.
@@ -196,7 +228,7 @@ class HTMLLogger(BaseLogger):
                                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:
@@ -204,7 +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>'
 
-        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:
@@ -220,6 +252,10 @@ class TextLogger(BaseLogger):
         self.buffer = io.StringIO()
 
 
+    def _timestamp(self) -> None:
+        self._write(f'[{dt.datetime.now()}]\n')
+
+
     def get_buffer(self) -> str:
         return self.buffer.getvalue()
 
@@ -232,6 +268,7 @@ class TextLogger(BaseLogger):
 
 
     def section(self, heading: str) -> None:
+        self._timestamp()
         self._write(f"\n# {heading}\n\n")
 
 
@@ -268,6 +305,7 @@ class TextLogger(BaseLogger):
 
 
     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:
@@ -283,6 +321,7 @@ class TextLogger(BaseLogger):
 
     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")