base_url configuration setting, closes #394

* base_url configuration setting * base_url works for static assets as well
simonw · Mar 25, 2020 · 7656fd6 · 7656fd6
1 parent 2a36dfa
commit 7656fd6
Show file tree

Hide file tree

Showing 15 changed files with 104 additions and 28 deletions.
diff --git a/datasette/app.py b/datasette/app.py
@@ -135,7 +135,9 @@
         False,
         "Allow display of template debug information with ?_context=1",
     ),
+    ConfigOption("base_url", "/", "Datasette URLs should use this base"),
 )
+
 DEFAULT_CONFIG = {option.name: option.default for option in CONFIG_OPTIONS}
 
 
@@ -573,6 +575,7 @@ async def render_template(
                 "format_bytes": format_bytes,
                 "extra_css_urls": self._asset_urls("extra_css_urls", template, context),
                 "extra_js_urls": self._asset_urls("extra_js_urls", template, context),
+                "base_url": self.config("base_url"),
             },
             **extra_template_vars,
         }
@@ -736,6 +739,13 @@ def __init__(self, datasette, routes):
         self.ds = datasette
         super().__init__(routes)
 
+    async def route_path(self, scope, receive, send, path):
+        # Strip off base_url if present before routing
+        base_url = self.ds.config("base_url")
+        if base_url != "/" and path.startswith(base_url):
+            path = "/" + path[len(base_url) :]
+        return await super().route_path(scope, receive, send, path)
+
     async def handle_404(self, scope, receive, send):
         # If URL has a trailing slash, redirect to URL without it
         path = scope.get("raw_path", scope["path"].encode("utf8"))

diff --git a/datasette/cli.py b/datasette/cli.py
@@ -27,7 +27,7 @@ def convert(self, config, param, ctx):
         if ":" not in config:
             self.fail('"{}" should be name:value'.format(config), param, ctx)
             return
-        name, value = config.split(":")
+        name, value = config.split(":", 1)
         if name not in DEFAULT_CONFIG:
             self.fail(
                 "{} is not a valid option (--help-config to see all)".format(name),
@@ -50,6 +50,8 @@ def convert(self, config, param, ctx):
                 self.fail('"{}" should be an integer'.format(name), param, ctx)
                 return
             return name, int(value)
+        elif isinstance(default, str):
+            return name, value
         else:
             # Should never happen:
             self.fail("Invalid option")

diff --git a/datasette/templates/_codemirror.html b/datasette/templates/_codemirror.html
@@ -1,7 +1,7 @@
-<script src="/-/static/sql-formatter-2.3.3.min.js" defer></script>
+<script src="{{ base_url }}-/static/sql-formatter-2.3.3.min.js" defer></script>
-<script src="/-/static/codemirror-5.31.0.js"></script>
+<script src="{{ base_url }}-/static/codemirror-5.31.0.js"></script>
-<link rel="stylesheet" href="/-/static/codemirror-5.31.0-min.css" />
+<link rel="stylesheet" href="{{ base_url }}-/static/codemirror-5.31.0-min.css" />
-<script src="/-/static/codemirror-5.31.0-sql.min.js"></script>
+<script src="{{ base_url }}-/static/codemirror-5.31.0-sql.min.js"></script>
 <style>
     .CodeMirror { height: auto; min-height: 70px; width: 80%; border: 1px solid #ddd; }
     .CodeMirror-scroll { max-height: 200px; }

diff --git a/datasette/templates/base.html b/datasette/templates/base.html
@@ -2,7 +2,7 @@
 <html>
 <head>
     <title>{% block title %}{% endblock %}</title>
-    <link rel="stylesheet" href="/-/static/app.css?{{ app_css_hash }}">
+    <link rel="stylesheet" href="{{ base_url }}-/static/app.css?{{ app_css_hash }}">
     <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
 {% for url in extra_css_urls %}
     <link rel="stylesheet" href="{{ url.url }}"{% if url.sri %} integrity="{{ url.sri }}" crossorigin="anonymous"{% endif %}>

diff --git a/datasette/templates/database.html b/datasette/templates/database.html
@@ -11,7 +11,7 @@
 
 {% block nav %}
     <p class="crumbs">
-        <a href="/">home</a>
+        <a href="{{ base_url }}">home</a>
     </p>
     {{ super() }}
 {% endblock %}

diff --git a/datasette/templates/row.html b/datasette/templates/row.html
@@ -17,7 +17,7 @@
 
 {% block nav %}
     <p class="crumbs">
-        <a href="/">home</a> /
+        <a href="{{ base_url }}">home</a> /
         <a href="{{ database_url(database) }}">{{ database }}</a> /
         <a href="{{ database_url(database) }}/{{ table|quote_plus }}">{{ table }}</a>
     </p>

diff --git a/datasette/templates/table.html b/datasette/templates/table.html
@@ -18,7 +18,7 @@
 
 {% block nav %}
     <p class="crumbs">
-        <a href="/">home</a> /
+        <a href="{{ base_url }}">home</a> /
         <a href="{{ database_url(database) }}">{{ database }}</a>
     </p>
     {{ super() }}

diff --git a/datasette/utils/asgi.py b/datasette/utils/asgi.py
@@ -110,6 +110,9 @@ async def __call__(self, scope, receive, send):
         raw_path = scope.get("raw_path")
         if raw_path:
             path = raw_path.decode("ascii")
+        return await self.route_path(scope, receive, send, path)
+
+    async def route_path(self, scope, receive, send, path):
         for regex, view in self.routes:
             match = regex.match(path)
             if match is not None:

diff --git a/datasette/views/base.py b/datasette/views/base.py
@@ -64,10 +64,11 @@ async def head(self, *args, **kwargs):
 
     def database_url(self, database):
         db = self.ds.databases[database]
+        base_url = self.ds.config("base_url")
         if self.ds.config("hash_urls") and db.hash:
-            return "/{}-{}".format(database, db.hash[:HASH_LENGTH])
+            return "{}{}-{}".format(base_url, database, db.hash[:HASH_LENGTH])
         else:
-            return "/{}".format(database)
+            return "{}{}".format(base_url, database)
 
     def database_color(self, database):
         return "ff0000"

diff --git a/datasette/views/table.py b/datasette/views/table.py
@@ -28,9 +28,9 @@
 from .base import DataView, DatasetteError, ureg
 
 LINK_WITH_LABEL = (
-    '<a href="/{database}/{table}/{link_id}">{label}</a>&nbsp;<em>{id}</em>'
+    '<a href="{base_url}{database}/{table}/{link_id}">{label}</a>&nbsp;<em>{id}</em>'
 )
-LINK_WITH_VALUE = '<a href="/{database}/{table}/{link_id}">{id}</a>'
+LINK_WITH_VALUE = '<a href="{base_url}{database}/{table}/{link_id}">{id}</a>'
 
 
 class Row:
@@ -100,6 +100,7 @@ async def display_columns_and_rows(
         }
 
         cell_rows = []
+        base_url = self.ds.config("base_url")
         for row in rows:
             cells = []
             # Unless we are a view, the first column is a link - either to the rowid
@@ -113,7 +114,8 @@ async def display_columns_and_rows(
                         "is_special_link_column": is_special_link_column,
                         "raw": pk_path,
                         "value": jinja2.Markup(
-                            '<a href="/{database}/{table}/{flat_pks_quoted}">{flat_pks}</a>'.format(
+                            '<a href="{base_url}{database}/{table}/{flat_pks_quoted}">{flat_pks}</a>'.format(
+                                base_url=base_url,
                                 database=database,
                                 table=urllib.parse.quote_plus(table),
                                 flat_pks=str(jinja2.escape(pk_path)),
@@ -159,6 +161,7 @@ async def display_columns_and_rows(
                     display_value = jinja2.Markup(
                         link_template.format(
                             database=database,
+                            base_url=base_url,
                             table=urllib.parse.quote_plus(other_table),
                             link_id=urllib.parse.quote_plus(str(value)),
                             id=str(jinja2.escape(value)),

diff --git a/docs/config.rst b/docs/config.rst
@@ -228,3 +228,16 @@ Some examples:
 * https://latest.datasette.io/?_context=1
 * https://latest.datasette.io/fixtures?_context=1
 * https://latest.datasette.io/fixtures/roadside_attractions?_context=1
+
+.. _config_base_url:
+
+base_url
+--------
+
+If you are running Datasette behind a proxy, it may be useful to change the root URL used for the Datasette instance.
+
+For example, if you are sending traffic from `https://www.example.com/tools/datasette/` through to a proxied Datasette instance you may wish Datasette to use `/tools/datasette/` as its root URL.
+
+You can do that like so::
+
+    datasette mydatabase.db --config base_url:/tools/datasette/
diff --git a/tests/fixtures.py b/tests/fixtures.py
@@ -351,7 +351,7 @@ def prepare_connection_args():
 
 @hookimpl
 def extra_css_urls(template, database, table, datasette):
-    return ['https://example.com/{}/extra-css-urls-demo.css'.format(
+    return ['https://plugin-example.com/{}/extra-css-urls-demo.css'.format(
         base64.b64encode(json.dumps({
             "template": template,
             "database": database,
@@ -363,9 +363,9 @@ def extra_css_urls(template, database, table, datasette):
 @hookimpl
 def extra_js_urls():
     return [{
-        'url': 'https://example.com/jquery.js',
+        'url': 'https://plugin-example.com/jquery.js',
         'sri': 'SRIHASH',
-    }, 'https://example.com/plugin1.js']
+    }, 'https://plugin-example.com/plugin1.js']
 
 
 @hookimpl
@@ -421,9 +421,9 @@ def extra_template_vars(template, database, table, view_name, request, datasette
 @hookimpl
 def extra_js_urls():
     return [{
-        'url': 'https://example.com/jquery.js',
+        'url': 'https://plugin-example.com/jquery.js',
         'sri': 'SRIHASH',
-    }, 'https://example.com/plugin2.js']
+    }, 'https://plugin-example.com/plugin2.js']
 
 
 @hookimpl

diff --git a/tests/test_api.py b/tests/test_api.py
@@ -1307,6 +1307,7 @@ def test_config_json(app_client):
         "force_https_urls": False,
         "hash_urls": False,
         "template_debug": False,
+        "base_url": "/",
     } == response.json
 
 

diff --git a/tests/test_html.py b/tests/test_html.py
@@ -1157,3 +1157,46 @@ def test_metadata_sort_desc(app_client):
     table = Soup(response.body, "html.parser").find("table")
     rows = [[str(td) for td in tr.select("td")] for tr in table.select("tbody tr")]
     assert list(reversed(expected)) == rows
+
+
+@pytest.mark.parametrize("base_url", ["/prefix/", "https://example.com/"])
+@pytest.mark.parametrize(
+    "path",
+    [
+        "/",
+        "/fixtures",
+        "/fixtures/compound_three_primary_keys",
+        "/fixtures/compound_three_primary_keys/a,a,a",
+        "/fixtures/paginated_view",
+    ],
+)
+def test_base_url_config(base_url, path):
+    for client in make_app_client(config={"base_url": base_url}):
+        response = client.get(base_url + path.lstrip("/"))
+        soup = Soup(response.body, "html.parser")
+        for el in soup.findAll(["a", "link", "script"]):
+            if "href" in el.attrs:
+                href = el["href"]
+            elif "src" in el.attrs:
+                href = el["src"]
+            else:
+                continue  # Could be a <script>...</script>
+            if (
+                not href.startswith("#")
+                and href
+                not in {
+                    "https://github.com/simonw/datasette",
+                    "https://github.com/simonw/datasette/blob/master/LICENSE",
+                    "https://github.com/simonw/datasette/blob/master/tests/fixtures.py",
+                }
+                and not href.startswith("https://plugin-example.com/")
+            ):
+                # If this has been made absolute it may start http://localhost/
+                if href.startswith("http://localhost/"):
+                    href = href[len("http://localost/") :]
+                assert href.startswith(base_url), {
+                    "base_url": base_url,
+                    "path": path,
+                    "href_or_src": href,
+                    "element_parent": str(el.parent),
+                }
diff --git a/tests/test_plugins.py b/tests/test_plugins.py
@@ -64,7 +64,7 @@ def test_plugin_extra_js_urls(app_client):
         == {
             "integrity": "SRIHASH",
             "crossorigin": "anonymous",
-            "src": "https://example.com/jquery.js",
+            "src": "https://plugin-example.com/jquery.js",
         }
     ]
 
@@ -74,24 +74,24 @@ def test_plugins_with_duplicate_js_urls(app_client):
     response = app_client.get("/fixtures")
     # This test is a little tricky, as if the user has any other plugins in
     # their current virtual environment those may affect what comes back too.
-    # What matters is that https://example.com/jquery.js is only there once
+    # What matters is that https://plugin-example.com/jquery.js is only there once
     # and it comes before plugin1.js and plugin2.js which could be in either
     # order
     scripts = Soup(response.body, "html.parser").findAll("script")
     srcs = [s["src"] for s in scripts if s.get("src")]
     # No duplicates allowed:
     assert len(srcs) == len(set(srcs))
     # jquery.js loaded once:
-    assert 1 == srcs.count("https://example.com/jquery.js")
+    assert 1 == srcs.count("https://plugin-example.com/jquery.js")
     # plugin1.js and plugin2.js are both there:
-    assert 1 == srcs.count("https://example.com/plugin1.js")
+    assert 1 == srcs.count("https://plugin-example.com/plugin1.js")
-    assert 1 == srcs.count("https://example.com/plugin2.js")
+    assert 1 == srcs.count("https://plugin-example.com/plugin2.js")
     # jquery comes before them both
-    assert srcs.index("https://example.com/jquery.js") < srcs.index(
+    assert srcs.index("https://plugin-example.com/jquery.js") < srcs.index(
-        "https://example.com/plugin1.js"
+        "https://plugin-example.com/plugin1.js"
     )
-    assert srcs.index("https://example.com/jquery.js") < srcs.index(
+    assert srcs.index("https://plugin-example.com/jquery.js") < srcs.index(
-        "https://example.com/plugin2.js"
+        "https://plugin-example.com/plugin2.js"
     )