def test_path_from_row_pks(row, pks, expected_path):
actual_path = utils.path_from_row_pks(row, pks, False)
assert expected_path == actual_path
def json_renderer(args, data, view_name):
""" Render a response as JSON """
status_code = 200
# Handle the _json= parameter which may modify data["rows"]
json_cols = []
if "_json" in args:
json_cols = args.getlist("_json")
if json_cols and "rows" in data and "columns" in data:
data["rows"] = convert_specific_columns_to_json(
data["rows"], data["columns"], json_cols)
# unless _json_infinity=1 requested, replace infinity with None
if "rows" in data and not value_as_boolean(args.get("_json_infinity",
"0")):
data["rows"] = [remove_infinites(row) for row in data["rows"]]
# Deal with the _shape option
shape = args.get("_shape", "arrays")
next_url = data.get("next_url")
if shape == "arrayfirst":
data = [row[0] for row in data["rows"]]
elif shape in ("objects", "object", "array"):
columns = data.get("columns")
rows = data.get("rows")
if rows and columns:
data["rows"] = [dict(zip(columns, row)) for row in rows]
if shape == "object":
error = None
if "primary_keys" not in data:
error = "_shape=object is only available on tables"
else:
pks = data["primary_keys"]
if not pks:
error = (
"_shape=object not available for tables with no primary keys"
)
else:
object_rows = {}
for row in data["rows"]:
pk_string = path_from_row_pks(row, pks, not pks)
object_rows[pk_string] = row
data = object_rows
if error:
data = {"ok": False, "error": error}
elif shape == "array":
data = data["rows"]
elif shape == "arrays":
pass
else:
status_code = 400
data = {
"ok": False,
"error": f"Invalid _shape: {shape}",
"status": 400,
"title": None,
}
# Handle _nl option for _shape=array
nl = args.get("_nl", "")
if nl and shape == "array":
body = "\n".join(
json.dumps(item, cls=CustomJSONEncoder) for item in data)
content_type = "text/plain"
else:
body = json.dumps(data, cls=CustomJSONEncoder)
content_type = "application/json; charset=utf-8"
headers = {}
if next_url:
headers["link"] = f'<{next_url}>; rel="next"'
return Response(body,
status=status_code,
headers=headers,
content_type=content_type)
async def data(
self,
request,
database,
hash,
table,
default_labels=False,
_next=None,
_size=None,
):
canned_query = await self.ds.get_canned_query(database, table, request.actor)
if canned_query:
return await QueryView(self.ds).data(
request,
database,
hash,
canned_query["sql"],
metadata=canned_query,
editable=False,
canned_query=table,
named_parameters=canned_query.get("params"),
write=bool(canned_query.get("write")),
)
db = self.ds.databases[database]
is_view = bool(await db.get_view_definition(table))
table_exists = bool(await db.table_exists(table))
if not is_view and not table_exists:
raise NotFound("Table not found: {}".format(table))
await self.check_permission(request, "view-instance")
await self.check_permission(request, "view-database", database)
await self.check_permission(request, "view-table", (database, table))
private = not await self.ds.permission_allowed(
None, "view-table", (database, table), default=True
)
pks = await db.primary_keys(table)
table_columns = await db.table_columns(table)
select_columns = ", ".join(escape_sqlite(t) for t in table_columns)
use_rowid = not pks and not is_view
if use_rowid:
select = "rowid, {}".format(select_columns)
order_by = "rowid"
order_by_pks = "rowid"
else:
select = select_columns
order_by_pks = ", ".join([escape_sqlite(pk) for pk in pks])
order_by = order_by_pks
if is_view:
order_by = ""
# Ensure we don't drop anything with an empty value e.g. ?name__exact=
args = MultiParams(
urllib.parse.parse_qs(request.query_string, keep_blank_values=True)
)
# Special args start with _ and do not contain a __
# That's so if there is a column that starts with _
# it can still be queried using ?_col__exact=blah
special_args = {}
other_args = []
for key in args:
if key.startswith("_") and "__" not in key:
special_args[key] = args[key]
else:
for v in args.getlist(key):
other_args.append((key, v))
# Handle ?_filter_column and redirect, if present
redirect_params = filters_should_redirect(special_args)
if redirect_params:
return self.redirect(
request,
path_with_added_args(request, redirect_params),
forward_querystring=False,
)
# Spot ?_sort_by_desc and redirect to _sort_desc=(_sort)
if "_sort_by_desc" in special_args:
return self.redirect(
request,
path_with_added_args(
request,
{
"_sort_desc": special_args.get("_sort"),
"_sort_by_desc": None,
"_sort": None,
},
),
forward_querystring=False,
)
table_metadata = self.ds.table_metadata(database, table)
units = table_metadata.get("units", {})
filters = Filters(sorted(other_args), units, ureg)
where_clauses, params = filters.build_where_clauses(table)
extra_wheres_for_ui = []
# Add _where= from querystring
if "_where" in request.args:
if not await self.ds.permission_allowed(
request.actor, "execute-sql", resource=database, default=True,
):
raise DatasetteError("_where= is not allowed", status=403)
else:
where_clauses.extend(request.args.getlist("_where"))
extra_wheres_for_ui = [
{
"text": text,
"remove_url": path_with_removed_args(request, {"_where": text}),
}
for text in request.args.getlist("_where")
]
# Support for ?_through={table, column, value}
extra_human_descriptions = []
if "_through" in request.args:
for through in request.args.getlist("_through"):
through_data = json.loads(through)
through_table = through_data["table"]
other_column = through_data["column"]
value = through_data["value"]
outgoing_foreign_keys = await db.foreign_keys_for_table(through_table)
try:
fk_to_us = [
fk for fk in outgoing_foreign_keys if fk["other_table"] == table
][0]
except IndexError:
raise DatasetteError(
"Invalid _through - could not find corresponding foreign key"
)
param = "p{}".format(len(params))
where_clauses.append(
"{our_pk} in (select {our_column} from {through_table} where {other_column} = :{param})".format(
through_table=escape_sqlite(through_table),
our_pk=escape_sqlite(fk_to_us["other_column"]),
our_column=escape_sqlite(fk_to_us["column"]),
other_column=escape_sqlite(other_column),
param=param,
)
)
params[param] = value
extra_human_descriptions.append(
'{}.{} = "{}"'.format(through_table, other_column, value)
)
# _search support:
fts_table = special_args.get("_fts_table")
fts_table = fts_table or table_metadata.get("fts_table")
fts_table = fts_table or await db.fts_table(table)
fts_pk = special_args.get("_fts_pk", table_metadata.get("fts_pk", "rowid"))
search_args = dict(
pair for pair in special_args.items() if pair[0].startswith("_search")
)
search = ""
search_mode_raw = special_args.get("_searchmode") == "raw"
if fts_table and search_args:
if "_search" in search_args:
# Simple ?_search=xxx
search = search_args["_search"]
where_clauses.append(
"{fts_pk} in (select rowid from {fts_table} where {fts_table} match {match_clause})".format(
fts_table=escape_sqlite(fts_table),
fts_pk=escape_sqlite(fts_pk),
match_clause=":search"
if search_mode_raw
else "escape_fts(:search)",
)
)
extra_human_descriptions.append('search matches "{}"'.format(search))
params["search"] = search
else:
# More complex: search against specific columns
for i, (key, search_text) in enumerate(search_args.items()):
search_col = key.split("_search_", 1)[1]
if search_col not in await db.table_columns(fts_table):
raise DatasetteError("Cannot search by that column", status=400)
where_clauses.append(
"rowid in (select rowid from {fts_table} where {search_col} match {match_clause})".format(
fts_table=escape_sqlite(fts_table),
search_col=escape_sqlite(search_col),
match_clause=":search_{}".format(i)
if search_mode_raw
else "escape_fts(:search_{})".format(i),
)
)
extra_human_descriptions.append(
'search column "{}" matches "{}"'.format(
search_col, search_text
)
)
params["search_{}".format(i)] = search_text
sortable_columns = set()
sortable_columns = await self.sortable_columns_for_table(
database, table, use_rowid
)
# Allow for custom sort order
sort = special_args.get("_sort")
sort_desc = special_args.get("_sort_desc")
if not sort and not sort_desc:
sort = table_metadata.get("sort")
sort_desc = table_metadata.get("sort_desc")
if sort and sort_desc:
raise DatasetteError("Cannot use _sort and _sort_desc at the same time")
if sort:
if sort not in sortable_columns:
raise DatasetteError("Cannot sort table by {}".format(sort))
order_by = escape_sqlite(sort)
if sort_desc:
if sort_desc not in sortable_columns:
raise DatasetteError("Cannot sort table by {}".format(sort_desc))
order_by = "{} desc".format(escape_sqlite(sort_desc))
from_sql = "from {table_name} {where}".format(
table_name=escape_sqlite(table),
where=("where {} ".format(" and ".join(where_clauses)))
if where_clauses
else "",
)
# Copy of params so we can mutate them later:
from_sql_params = dict(**params)
count_sql = "select count(*) {}".format(from_sql)
_next = _next or special_args.get("_next")
offset = ""
if _next:
if is_view:
# _next is an offset
offset = " offset {}".format(int(_next))
else:
components = urlsafe_components(_next)
# If a sort order is applied, the first of these is the sort value
if sort or sort_desc:
sort_value = components[0]
# Special case for if non-urlencoded first token was $null
if _next.split(",")[0] == "$null":
sort_value = None
components = components[1:]
# Figure out the SQL for next-based-on-primary-key first
next_by_pk_clauses = []
if use_rowid:
next_by_pk_clauses.append("rowid > :p{}".format(len(params)))
params["p{}".format(len(params))] = components[0]
else:
# Apply the tie-breaker based on primary keys
if len(components) == len(pks):
param_len = len(params)
next_by_pk_clauses.append(
compound_keys_after_sql(pks, param_len)
)
for i, pk_value in enumerate(components):
params["p{}".format(param_len + i)] = pk_value
# Now add the sort SQL, which may incorporate next_by_pk_clauses
if sort or sort_desc:
if sort_value is None:
if sort_desc:
# Just items where column is null ordered by pk
where_clauses.append(
"({column} is null and {next_clauses})".format(
column=escape_sqlite(sort_desc),
next_clauses=" and ".join(next_by_pk_clauses),
)
)
else:
where_clauses.append(
"({column} is not null or ({column} is null and {next_clauses}))".format(
column=escape_sqlite(sort),
next_clauses=" and ".join(next_by_pk_clauses),
)
)
else:
where_clauses.append(
"({column} {op} :p{p}{extra_desc_only} or ({column} = :p{p} and {next_clauses}))".format(
column=escape_sqlite(sort or sort_desc),
op=">" if sort else "<",
p=len(params),
extra_desc_only=""
if sort
else " or {column2} is null".format(
column2=escape_sqlite(sort or sort_desc)
),
next_clauses=" and ".join(next_by_pk_clauses),
)
)
params["p{}".format(len(params))] = sort_value
order_by = "{}, {}".format(order_by, order_by_pks)
else:
where_clauses.extend(next_by_pk_clauses)
where_clause = ""
if where_clauses:
where_clause = "where {} ".format(" and ".join(where_clauses))
if order_by:
order_by = "order by {} ".format(order_by)
extra_args = {}
# Handle ?_size=500
page_size = _size or request.args.get("_size") or table_metadata.get("size")
if page_size:
if page_size == "max":
page_size = self.ds.max_returned_rows
try:
page_size = int(page_size)
if page_size < 0:
raise ValueError
except ValueError:
raise DatasetteError("_size must be a positive integer", status=400)
if page_size > self.ds.max_returned_rows:
raise DatasetteError(
"_size must be <= {}".format(self.ds.max_returned_rows), status=400
)
extra_args["page_size"] = page_size
else:
page_size = self.ds.page_size
sql_no_limit = "select {select} from {table_name} {where}{order_by}".format(
select=select,
table_name=escape_sqlite(table),
where=where_clause,
order_by=order_by,
)
sql = "{sql_no_limit} limit {limit}{offset}".format(
sql_no_limit=sql_no_limit.rstrip(), limit=page_size + 1, offset=offset
)
if request.args.get("_timelimit"):
extra_args["custom_time_limit"] = int(request.args.get("_timelimit"))
results = await db.execute(sql, params, truncate=True, **extra_args)
# Number of filtered rows in whole set:
filtered_table_rows_count = None
if (
not db.is_mutable
and self.ds.inspect_data
and count_sql == "select count(*) from {} ".format(table)
):
try:
filtered_table_rows_count = self.ds.inspect_data[database]["tables"][
table
]["count"]
except KeyError:
pass
if count_sql and filtered_table_rows_count is None:
try:
count_rows = list(await db.execute(count_sql, from_sql_params))
filtered_table_rows_count = count_rows[0][0]
except QueryInterrupted:
pass
# facets support
if not self.ds.config("allow_facet") and any(
arg.startswith("_facet") for arg in request.args
):
raise DatasetteError("_facet= is not allowed", status=400)
# pylint: disable=no-member
facet_classes = list(
itertools.chain.from_iterable(pm.hook.register_facet_classes())
)
facet_results = {}
facets_timed_out = []
facet_instances = []
for klass in facet_classes:
facet_instances.append(
klass(
self.ds,
request,
database,
sql=sql_no_limit,
params=params,
table=table,
metadata=table_metadata,
row_count=filtered_table_rows_count,
)
)
for facet in facet_instances:
(
instance_facet_results,
instance_facets_timed_out,
) = await facet.facet_results()
facet_results.update(instance_facet_results)
facets_timed_out.extend(instance_facets_timed_out)
# Figure out columns and rows for the query
columns = [r[0] for r in results.description]
rows = list(results.rows)
# Expand labeled columns if requested
expanded_columns = []
expandable_columns = await self.expandable_columns(database, table)
columns_to_expand = None
try:
all_labels = value_as_boolean(special_args.get("_labels", ""))
except ValueError:
all_labels = default_labels
# Check for explicit _label=
if "_label" in request.args:
columns_to_expand = request.args.getlist("_label")
if columns_to_expand is None and all_labels:
# expand all columns with foreign keys
columns_to_expand = [fk["column"] for fk, _ in expandable_columns]
if columns_to_expand:
expanded_labels = {}
for fk, _ in expandable_columns:
column = fk["column"]
if column not in columns_to_expand:
continue
expanded_columns.append(column)
# Gather the values
column_index = columns.index(column)
values = [row[column_index] for row in rows]
# Expand them
expanded_labels.update(
await self.ds.expand_foreign_keys(database, table, column, values)
)
if expanded_labels:
# Rewrite the rows
new_rows = []
for row in rows:
new_row = CustomRow(columns)
for column in row.keys():
value = row[column]
if (column, value) in expanded_labels and value is not None:
new_row[column] = {
"value": value,
"label": expanded_labels[(column, value)],
}
else:
new_row[column] = value
new_rows.append(new_row)
rows = new_rows
# Pagination next link
next_value = None
next_url = None
if len(rows) > page_size and page_size > 0:
if is_view:
next_value = int(_next or 0) + page_size
else:
next_value = path_from_row_pks(rows[-2], pks, use_rowid)
# If there's a sort or sort_desc, add that value as a prefix
if (sort or sort_desc) and not is_view:
prefix = rows[-2][sort or sort_desc]
if isinstance(prefix, dict) and "value" in prefix:
prefix = prefix["value"]
if prefix is None:
prefix = "$null"
else:
prefix = urllib.parse.quote_plus(str(prefix))
next_value = "{},{}".format(prefix, next_value)
added_args = {"_next": next_value}
if sort:
added_args["_sort"] = sort
else:
added_args["_sort_desc"] = sort_desc
else:
added_args = {"_next": next_value}
next_url = self.ds.absolute_url(
request, path_with_replaced_args(request, added_args)
)
rows = rows[:page_size]
# Detect suggested facets
suggested_facets = []
if (
self.ds.config("suggest_facets")
and self.ds.config("allow_facet")
and not _next
):
for facet in facet_instances:
suggested_facets.extend(await facet.suggest())
# human_description_en combines filters AND search, if provided
human_description_en = filters.human_description_en(
extra=extra_human_descriptions
)
if sort or sort_desc:
sorted_by = "sorted by {}{}".format(
(sort or sort_desc), " descending" if sort_desc else ""
)
human_description_en = " ".join(
[b for b in [human_description_en, sorted_by] if b]
)
async def extra_template():
nonlocal sort
display_columns, display_rows = await self.display_columns_and_rows(
database,
table,
results.description,
rows,
link_column=not is_view,
truncate_cells=self.ds.config("truncate_cells_html"),
)
metadata = (
(self.ds.metadata("databases") or {})
.get(database, {})
.get("tables", {})
.get(table, {})
)
self.ds.update_with_inherited_metadata(metadata)
form_hidden_args = []
for arg in ("_fts_table", "_fts_pk"):
if arg in special_args:
form_hidden_args.append((arg, special_args[arg]))
if request.args.get("_where"):
for where_text in request.args.getlist("_where"):
form_hidden_args.append(("_where", where_text))
# if no sort specified AND table has a single primary key,
# set sort to that so arrow is displayed
if not sort and not sort_desc:
if 1 == len(pks):
sort = pks[0]
elif use_rowid:
sort = "rowid"
return {
"supports_search": bool(fts_table),
"search": search or "",
"use_rowid": use_rowid,
"filters": filters,
"display_columns": display_columns,
"filter_columns": columns,
"display_rows": display_rows,
"facets_timed_out": facets_timed_out,
"sorted_facet_results": sorted(
facet_results.values(),
key=lambda f: (len(f["results"]), f["name"]),
reverse=True,
),
"extra_wheres_for_ui": extra_wheres_for_ui,
"form_hidden_args": form_hidden_args,
"is_sortable": any(c["sortable"] for c in display_columns),
"path_with_replaced_args": path_with_replaced_args,
"path_with_removed_args": path_with_removed_args,
"append_querystring": append_querystring,
"request": request,
"sort": sort,
"sort_desc": sort_desc,
"disable_sort": is_view,
"custom_table_templates": [
"_table-{}-{}.html".format(
to_css_class(database), to_css_class(table)
),
"_table-table-{}-{}.html".format(
to_css_class(database), to_css_class(table)
),
"_table.html",
],
"metadata": metadata,
"view_definition": await db.get_view_definition(table),
"table_definition": await db.get_table_definition(table),
}
return (
{
"database": database,
"table": table,
"is_view": is_view,
"human_description_en": human_description_en,
"rows": rows[:page_size],
"truncated": results.truncated,
"filtered_table_rows_count": filtered_table_rows_count,
"expanded_columns": expanded_columns,
"expandable_columns": expandable_columns,
"columns": columns,
"primary_keys": pks,
"units": units,
"query": {"sql": sql, "params": params},
"facet_results": facet_results,
"suggested_facets": suggested_facets,
"next": next_value and str(next_value) or None,
"next_url": next_url,
"private": private,
"allow_execute_sql": await self.ds.permission_allowed(
request.actor, "execute-sql", database, default=True
),
},
extra_template,
(
"table-{}-{}.html".format(to_css_class(database), to_css_class(table)),
"table.html",
),
)
async def display_columns_and_rows(
self, database, table, description, rows, link_column=False, truncate_cells=0
):
"Returns columns, rows for specified table - including fancy foreign key treatment"
db = self.ds.databases[database]
table_metadata = self.ds.table_metadata(database, table)
sortable_columns = await self.sortable_columns_for_table(database, table, True)
columns = [
{"name": r[0], "sortable": r[0] in sortable_columns} for r in description
]
pks = await db.primary_keys(table)
column_to_foreign_key_table = {
fk["column"]: fk["other_table"]
for fk in await db.foreign_keys_for_table(table)
}
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
# or to the simple or compound primary key
if link_column:
is_special_link_column = len(pks) != 1
pk_path = path_from_row_pks(row, pks, not pks, False)
cells.append(
{
"column": pks[0] if len(pks) == 1 else "Link",
"value_type": "pk",
"is_special_link_column": is_special_link_column,
"raw": pk_path,
"value": jinja2.Markup(
'<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)),
flat_pks_quoted=path_from_row_pks(row, pks, not pks),
)
),
}
)
for value, column_dict in zip(row, columns):
column = column_dict["name"]
if link_column and len(pks) == 1 and column == pks[0]:
# If there's a simple primary key, don't repeat the value as it's
# already shown in the link column.
continue
# First let the plugins have a go
# pylint: disable=no-member
plugin_display_value = pm.hook.render_cell(
value=value,
column=column,
table=table,
database=database,
datasette=self.ds,
)
if plugin_display_value is not None:
display_value = plugin_display_value
elif isinstance(value, bytes):
display_value = jinja2.Markup(
"<Binary data: {} byte{}>".format(
len(value), "" if len(value) == 1 else "s"
)
)
elif isinstance(value, dict):
# It's an expanded foreign key - display link to other row
label = value["label"]
value = value["value"]
# The table we link to depends on the column
other_table = column_to_foreign_key_table[column]
link_template = (
LINK_WITH_LABEL if (label != value) else LINK_WITH_VALUE
)
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)),
label=str(jinja2.escape(label)),
)
)
elif value in ("", None):
display_value = jinja2.Markup(" ")
elif is_url(str(value).strip()):
display_value = jinja2.Markup(
'<a href="{url}">{url}</a>'.format(
url=jinja2.escape(value.strip())
)
)
elif column in table_metadata.get("units", {}) and value != "":
# Interpret units using pint
value = value * ureg(table_metadata["units"][column])
# Pint uses floating point which sometimes introduces errors in the compact
# representation, which we have to round off to avoid ugliness. In the vast
# majority of cases this rounding will be inconsequential. I hope.
value = round(value.to_compact(), 6)
display_value = jinja2.Markup(
"{:~P}".format(value).replace(" ", " ")
)
else:
display_value = str(value)
if truncate_cells and len(display_value) > truncate_cells:
display_value = display_value[:truncate_cells] + u"\u2026"
cells.append(
{
"column": column,
"value": display_value,
"raw": value,
"value_type": "none"
if value is None
else str(type(value).__name__),
}
)
cell_rows.append(Row(cells))
if link_column:
# Add the link column header.
# If it's a simple primary key, we have to remove and re-add that column name at
# the beginning of the header row.
if len(pks) == 1:
columns = [col for col in columns if col["name"] != pks[0]]
columns = [
{"name": pks[0] if len(pks) == 1 else "Link", "sortable": len(pks) == 1}
] + columns
return columns, cell_rows
async def view_get(self, request, name, hash, **kwargs):
try:
as_json = kwargs.pop("as_json")
except KeyError:
as_json = False
extra_template_data = {}
start = time.time()
status_code = 200
templates = []
try:
response_or_template_contexts = await self.data(
request, name, hash, **kwargs)
if isinstance(response_or_template_contexts,
response.HTTPResponse):
return response_or_template_contexts
else:
data, extra_template_data, templates = response_or_template_contexts
except InterruptedError as e:
raise DatasetteError(str(e), title="SQL Interrupted", status=400)
except (sqlite3.OperationalError, InvalidSql) as e:
raise DatasetteError(str(e), title="Invalid SQL", status=400)
except (sqlite3.OperationalError) as e:
raise DatasetteError(str(e))
except DatasetteError:
raise
end = time.time()
data["query_ms"] = (end - start) * 1000
for key in ("source", "source_url", "license", "license_url"):
value = self.ds.metadata.get(key)
if value:
data[key] = value
if as_json:
# Special case for .jsono extension - redirect to _shape=objects
if as_json == ".jsono":
return self.redirect(
request,
path_with_added_args(
request,
{"_shape": "objects"},
path=request.path.rsplit(".jsono", 1)[0] + ".json",
),
forward_querystring=False,
)
# Deal with the _shape option
shape = request.args.get("_shape", "arrays")
if shape in ("objects", "object", "array"):
columns = data.get("columns")
rows = data.get("rows")
if rows and columns:
data["rows"] = [dict(zip(columns, row)) for row in rows]
if shape == "object":
error = None
if "primary_keys" not in data:
error = "_shape=object is only available on tables"
else:
pks = data["primary_keys"]
if not pks:
error = "_shape=object not available for tables with no primary keys"
else:
object_rows = {}
for row in data["rows"]:
pk_string = path_from_row_pks(
row, pks, not pks)
object_rows[pk_string] = row
data = object_rows
if error:
data = {
"ok": False,
"error": error,
"database": name,
"database_hash": hash,
}
elif shape == "array":
data = data["rows"]
elif shape == "arrays":
pass
else:
status_code = 400
data = {
"ok": False,
"error": "Invalid _shape: {}".format(shape),
"status": 400,
"title": None,
}
headers = {}
if self.ds.cors:
headers["Access-Control-Allow-Origin"] = "*"
r = response.HTTPResponse(
json.dumps(data, cls=CustomJSONEncoder),
status=status_code,
content_type="application/json",
headers=headers,
)
else:
extras = {}
if callable(extra_template_data):
extras = extra_template_data()
if asyncio.iscoroutine(extras):
extras = await extras
else:
extras = extra_template_data
context = {
**data,
**extras,
**{
"url_json": path_with_ext(request, ".json"),
"url_jsono": path_with_ext(request, ".jsono"),
"extra_css_urls": self.ds.extra_css_urls(),
"extra_js_urls": self.ds.extra_js_urls(),
"datasette_version": __version__,
}
}
if "metadata" not in context:
context["metadata"] = self.ds.metadata
r = self.render(templates, **context)
r.status = status_code
# Set far-future cache expiry
if self.ds.cache_headers:
r.headers["Cache-Control"] = "max-age={}".format(365 * 24 * 60 *
60)
return r
async def view_get(self, request, name, hash, **kwargs):
# If ?_format= is provided, use that as the format
_format = request.args.get("_format", None)
if not _format:
_format = (kwargs.pop("as_format", None) or "").lstrip(".")
if "table_and_format" in kwargs:
table, _ext_format = resolve_table_and_format(
table_and_format=urllib.parse.unquote_plus(
kwargs["table_and_format"]),
table_exists=lambda t: self.ds.table_exists(name, t))
_format = _format or _ext_format
kwargs["table"] = table
del kwargs["table_and_format"]
elif "table" in kwargs:
kwargs["table"] = urllib.parse.unquote_plus(kwargs["table"])
if _format == "csv":
return await self.as_csv(request, name, hash, **kwargs)
if _format is None:
# HTML views default to expanding all forign key labels
kwargs['default_labels'] = True
extra_template_data = {}
start = time.time()
status_code = 200
templates = []
try:
response_or_template_contexts = await self.data(
request, name, hash, **kwargs)
if isinstance(response_or_template_contexts,
response.HTTPResponse):
return response_or_template_contexts
else:
data, extra_template_data, templates = response_or_template_contexts
except InterruptedError as e:
raise DatasetteError("""
SQL query took too long. The time limit is controlled by the
<a href="https://datasette.readthedocs.io/en/stable/config.html#sql-time-limit-ms">sql_time_limit_ms</a>
configuration option.
""",
title="SQL Interrupted",
status=400,
messagge_is_html=True)
except (sqlite3.OperationalError, InvalidSql) as e:
raise DatasetteError(str(e), title="Invalid SQL", status=400)
except (sqlite3.OperationalError) as e:
raise DatasetteError(str(e))
except DatasetteError:
raise
end = time.time()
data["query_ms"] = (end - start) * 1000
for key in ("source", "source_url", "license", "license_url"):
value = self.ds.metadata.get(key)
if value:
data[key] = value
if _format in ("json", "jsono"):
# Special case for .jsono extension - redirect to _shape=objects
if _format == "jsono":
return self.redirect(
request,
path_with_added_args(
request,
{"_shape": "objects"},
path=request.path.rsplit(".jsono", 1)[0] + ".json",
),
forward_querystring=False,
)
# Handle the _json= parameter which may modify data["rows"]
json_cols = []
if "_json" in request.args:
json_cols = request.args["_json"]
if json_cols and "rows" in data and "columns" in data:
data["rows"] = convert_specific_columns_to_json(
data["rows"],
data["columns"],
json_cols,
)
# unless _json_infinity=1 requested, replace infinity with None
if "rows" in data and not value_as_boolean(
request.args.get("_json_infinity", "0")):
data["rows"] = [remove_infinites(row) for row in data["rows"]]
# Deal with the _shape option
shape = request.args.get("_shape", "arrays")
if shape == "arrayfirst":
data = [row[0] for row in data["rows"]]
elif shape in ("objects", "object", "array"):
columns = data.get("columns")
rows = data.get("rows")
if rows and columns:
data["rows"] = [dict(zip(columns, row)) for row in rows]
if shape == "object":
error = None
if "primary_keys" not in data:
error = "_shape=object is only available on tables"
else:
pks = data["primary_keys"]
if not pks:
error = "_shape=object not available for tables with no primary keys"
else:
object_rows = {}
for row in data["rows"]:
pk_string = path_from_row_pks(
row, pks, not pks)
object_rows[pk_string] = row
data = object_rows
if error:
data = {
"ok": False,
"error": error,
"database": name,
"database_hash": hash,
}
elif shape == "array":
data = data["rows"]
elif shape == "arrays":
pass
else:
status_code = 400
data = {
"ok": False,
"error": "Invalid _shape: {}".format(shape),
"status": 400,
"title": None,
}
headers = {}
if self.ds.cors:
headers["Access-Control-Allow-Origin"] = "*"
r = response.HTTPResponse(
json.dumps(data, cls=CustomJSONEncoder),
status=status_code,
content_type="application/json",
headers=headers,
)
else:
extras = {}
if callable(extra_template_data):
extras = extra_template_data()
if asyncio.iscoroutine(extras):
extras = await extras
else:
extras = extra_template_data
url_labels_extra = {}
if data.get("expandable_columns"):
url_labels_extra = {"_labels": "on"}
url_csv_args = {"_size": "max", **url_labels_extra}
url_csv = path_with_format(request, "csv", url_csv_args)
url_csv_path = url_csv.split('?')[0]
context = {
**data,
**extras,
**{
"url_json":
path_with_format(request, "json", {
**url_labels_extra,
}),
"url_csv":
url_csv,
"url_csv_path":
url_csv_path,
"url_csv_args":
url_csv_args,
"extra_css_urls":
self.ds.extra_css_urls(),
"extra_js_urls":
self.ds.extra_js_urls(),
"datasette_version":
__version__,
"config":
self.ds.config_dict(),
}
}
if "metadata" not in context:
context["metadata"] = self.ds.metadata
r = self.render(templates, **context)
r.status = status_code
# Set far-future cache expiry
if self.ds.cache_headers:
ttl = request.args.get("_ttl", None)
if ttl is None or not ttl.isdigit():
ttl = self.ds.config("default_cache_ttl")
else:
ttl = int(ttl)
if ttl == 0:
ttl_header = 'no-cache'
else:
ttl_header = 'max-age={}'.format(ttl)
r.headers["Cache-Control"] = ttl_header
r.headers["Referrer-Policy"] = "no-referrer"
return r
async def view_get(self, request, name, hash, **kwargs):
try:
as_json = kwargs.pop("as_json")
except KeyError:
as_json = False
extra_template_data = {}
start = time.time()
status_code = 200
templates = []
try:
response_or_template_contexts = await self.data(
request, name, hash, **kwargs
)
if isinstance(response_or_template_contexts, response.HTTPResponse):
return response_or_template_contexts
else:
data, extra_template_data, templates = response_or_template_contexts
except InterruptedError as e:
raise DatasetteError("""
SQL query took too long. The time limit is controlled by the
<a href="https://datasette.readthedocs.io/en/stable/config.html#sql-time-limit-ms">sql_time_limit_ms</a>
configuration option.
""", title="SQL Interrupted", status=400, messagge_is_html=True)
except (sqlite3.OperationalError, InvalidSql) as e:
raise DatasetteError(str(e), title="Invalid SQL", status=400)
except (sqlite3.OperationalError) as e:
raise DatasetteError(str(e))
except DatasetteError:
raise
end = time.time()
data["query_ms"] = (end - start) * 1000
for key in ("source", "source_url", "license", "license_url"):
value = self.ds.metadata.get(key)
if value:
data[key] = value
if as_json:
# Special case for .jsono extension - redirect to _shape=objects
if as_json == ".jsono":
return self.redirect(
request,
path_with_added_args(
request,
{"_shape": "objects"},
path=request.path.rsplit(".jsono", 1)[0] + ".json",
),
forward_querystring=False,
)
# Handle the _json= parameter which may modify data["rows"]
json_cols = []
if "_json" in request.args:
json_cols = request.args["_json"]
if json_cols and "rows" in data and "columns" in data:
data["rows"] = convert_specific_columns_to_json(
data["rows"], data["columns"], json_cols,
)
# Deal with the _shape option
shape = request.args.get("_shape", "arrays")
if shape == "arrayfirst":
data = [row[0] for row in data["rows"]]
elif shape in ("objects", "object", "array"):
columns = data.get("columns")
rows = data.get("rows")
if rows and columns:
data["rows"] = [dict(zip(columns, row)) for row in rows]
if shape == "object":
error = None
if "primary_keys" not in data:
error = "_shape=object is only available on tables"
else:
pks = data["primary_keys"]
if not pks:
error = "_shape=object not available for tables with no primary keys"
else:
object_rows = {}
for row in data["rows"]:
pk_string = path_from_row_pks(row, pks, not pks)
object_rows[pk_string] = row
data = object_rows
if error:
data = {
"ok": False,
"error": error,
"database": name,
"database_hash": hash,
}
elif shape == "array":
data = data["rows"]
elif shape == "arrays":
pass
else:
status_code = 400
data = {
"ok": False,
"error": "Invalid _shape: {}".format(shape),
"status": 400,
"title": None,
}
headers = {}
if self.ds.cors:
headers["Access-Control-Allow-Origin"] = "*"
r = response.HTTPResponse(
json.dumps(data, cls=CustomJSONEncoder),
status=status_code,
content_type="application/json",
headers=headers,
)
else:
extras = {}
if callable(extra_template_data):
extras = extra_template_data()
if asyncio.iscoroutine(extras):
extras = await extras
else:
extras = extra_template_data
context = {
**data,
**extras,
**{
"url_json": path_with_ext(request, ".json"),
"url_jsono": path_with_ext(request, ".jsono"),
"extra_css_urls": self.ds.extra_css_urls(),
"extra_js_urls": self.ds.extra_js_urls(),
"datasette_version": __version__,
}
}
if "metadata" not in context:
context["metadata"] = self.ds.metadata
r = self.render(templates, **context)
r.status = status_code
# Set far-future cache expiry
if self.ds.cache_headers:
ttl = request.args.get("_ttl", None)
if ttl is None or not ttl.isdigit():
ttl = self.ds.config["default_cache_ttl"]
else:
ttl = int(ttl)
if ttl == 0:
ttl_header = 'no-cache'
else:
ttl_header = 'max-age={}'.format(ttl)
r.headers["Cache-Control"] = ttl_header
r.headers["Referrer-Policy"] = "no-referrer"
return r
async def stream_fn(r):
nonlocal data
writer = csv.writer(LimitedWriter(r,
self.ds.setting("max_csv_mb")))
first = True
next = None
while first or (next and stream):
try:
if next:
kwargs["_next"] = next
if not first:
data, _, _ = await self.data(request, database, hash,
**kwargs)
if first:
await writer.writerow(headings)
first = False
next = data.get("next")
for row in data["rows"]:
if any(isinstance(r, bytes) for r in row):
new_row = []
for column, cell in zip(headings, row):
if isinstance(cell, bytes):
# If this is a table page, use .urls.row_blob()
if data.get("table"):
pks = data.get("primary_keys") or []
cell = self.ds.absolute_url(
request,
self.ds.urls.row_blob(
database,
data["table"],
path_from_row_pks(
row, pks, not pks),
column,
),
)
else:
# Otherwise generate URL for this query
cell = self.ds.absolute_url(
request,
path_with_format(
request=request,
format="blob",
extra_qs={
"_blob_column":
column,
"_blob_hash":
hashlib.sha256(
cell).hexdigest(),
},
replace_format="csv",
),
)
new_row.append(cell)
row = new_row
if not expanded_columns:
# Simple path
await writer.writerow(row)
else:
# Look for {"value": "label": } dicts and expand
new_row = []
for heading, cell in zip(data["columns"], row):
if heading in expanded_columns:
if cell is None:
new_row.extend(("", ""))
else:
assert isinstance(cell, dict)
new_row.append(cell["value"])
new_row.append(cell["label"])
else:
new_row.append(cell)
await writer.writerow(new_row)
except Exception as e:
print("caught this", e)
await r.write(str(e))
return
async def display_columns_and_rows(
datasette,
database_name,
table_name,
description,
rows,
link_column=False,
truncate_cells=0,
sortable_columns=None,
):
"""Returns columns, rows for specified table - including fancy foreign key treatment"""
sortable_columns = sortable_columns or set()
db = datasette.databases[database_name]
table_metadata = datasette.table_metadata(database_name, table_name)
column_descriptions = table_metadata.get("columns") or {}
column_details = {
col.name: col
for col in await db.table_column_details(table_name)
}
pks = await db.primary_keys(table_name)
pks_for_display = pks
if not pks_for_display:
pks_for_display = ["rowid"]
columns = []
for r in description:
if r[0] == "rowid" and "rowid" not in column_details:
type_ = "integer"
notnull = 0
else:
type_ = column_details[r[0]].type
notnull = column_details[r[0]].notnull
columns.append({
"name": r[0],
"sortable": r[0] in sortable_columns,
"is_pk": r[0] in pks_for_display,
"type": type_,
"notnull": notnull,
"description": column_descriptions.get(r[0]),
})
column_to_foreign_key_table = {
fk["column"]: fk["other_table"]
for fk in await db.foreign_keys_for_table(table_name)
}
cell_rows = []
base_url = datasette.setting("base_url")
for row in rows:
cells = []
# Unless we are a view, the first column is a link - either to the rowid
# or to the simple or compound primary key
if link_column:
is_special_link_column = len(pks) != 1
pk_path = path_from_row_pks(row, pks, not pks, False)
cells.append({
"column":
pks[0] if len(pks) == 1 else "Link",
"value_type":
"pk",
"is_special_link_column":
is_special_link_column,
"raw":
pk_path,
"value":
markupsafe.Markup(
'<a href="{table_path}/{flat_pks_quoted}">{flat_pks}</a>'.
format(
base_url=base_url,
table_path=datasette.urls.table(
database_name, table_name),
flat_pks=str(markupsafe.escape(pk_path)),
flat_pks_quoted=path_from_row_pks(row, pks, not pks),
)),
})
for value, column_dict in zip(row, columns):
column = column_dict["name"]
if link_column and len(pks) == 1 and column == pks[0]:
# If there's a simple primary key, don't repeat the value as it's
# already shown in the link column.
continue
# First let the plugins have a go
# pylint: disable=no-member
plugin_display_value = None
for candidate in pm.hook.render_cell(
value=value,
column=column,
table=table_name,
database=database_name,
datasette=datasette,
):
candidate = await await_me_maybe(candidate)
if candidate is not None:
plugin_display_value = candidate
break
if plugin_display_value:
display_value = plugin_display_value
elif isinstance(value, bytes):
formatted = format_bytes(len(value))
display_value = markupsafe.Markup(
'<a class="blob-download" href="{}"{}><Binary: {:,} byte{}></a>'
.format(
datasette.urls.row_blob(
database_name,
table_name,
path_from_row_pks(row, pks, not pks),
column,
),
' title="{}"'.format(formatted)
if "bytes" not in formatted else "",
len(value),
"" if len(value) == 1 else "s",
))
elif isinstance(value, dict):
# It's an expanded foreign key - display link to other row
label = value["label"]
value = value["value"]
# The table we link to depends on the column
other_table = column_to_foreign_key_table[column]
link_template = LINK_WITH_LABEL if (
label != value) else LINK_WITH_VALUE
display_value = markupsafe.Markup(
link_template.format(
database=database_name,
base_url=base_url,
table=tilde_encode(other_table),
link_id=tilde_encode(str(value)),
id=str(markupsafe.escape(value)),
label=str(markupsafe.escape(label)) or "-",
))
elif value in ("", None):
display_value = markupsafe.Markup(" ")
elif is_url(str(value).strip()):
display_value = markupsafe.Markup(
'<a href="{url}">{url}</a>'.format(
url=markupsafe.escape(value.strip())))
elif column in table_metadata.get("units", {}) and value != "":
# Interpret units using pint
value = value * ureg(table_metadata["units"][column])
# Pint uses floating point which sometimes introduces errors in the compact
# representation, which we have to round off to avoid ugliness. In the vast
# majority of cases this rounding will be inconsequential. I hope.
value = round(value.to_compact(), 6)
display_value = markupsafe.Markup(f"{value:~P}".replace(
" ", " "))
else:
display_value = str(value)
if truncate_cells and len(display_value) > truncate_cells:
display_value = display_value[:truncate_cells] + "\u2026"
cells.append({
"column":
column,
"value":
display_value,
"raw":
value,
"value_type":
"none" if value is None else str(type(value).__name__),
})
cell_rows.append(Row(cells))
if link_column:
# Add the link column header.
# If it's a simple primary key, we have to remove and re-add that column name at
# the beginning of the header row.
first_column = None
if len(pks) == 1:
columns = [col for col in columns if col["name"] != pks[0]]
first_column = {
"name": pks[0],
"sortable": len(pks) == 1,
"is_pk": True,
"type": column_details[pks[0]].type,
"notnull": column_details[pks[0]].notnull,
}
else:
first_column = {
"name": "Link",
"sortable": False,
"is_pk": False,
"type": "",
"notnull": 0,
}
columns = [first_column] + columns
return columns, cell_rows
def test_path_from_row_pks(row, pks, expected_path):
actual_path = utils.path_from_row_pks(row, pks, False)
assert expected_path == actual_path
async def _data_traced(
self,
request,
default_labels=False,
_next=None,
_size=None,
):
database_route = tilde_decode(request.url_vars["database"])
table_name = tilde_decode(request.url_vars["table"])
try:
db = self.ds.get_database(route=database_route)
except KeyError:
raise NotFound("Database not found: {}".format(database_route))
database_name = db.name
# For performance profiling purposes, ?_noparallel=1 turns off asyncio.gather
async def _gather_parallel(*args):
return await asyncio.gather(*args)
async def _gather_sequential(*args):
results = []
for fn in args:
results.append(await fn)
return results
gather = (_gather_sequential
if request.args.get("_noparallel") else _gather_parallel)
# If this is a canned query, not a table, then dispatch to QueryView instead
canned_query = await self.ds.get_canned_query(database_name,
table_name,
request.actor)
if canned_query:
return await QueryView(self.ds).data(
request,
canned_query["sql"],
metadata=canned_query,
editable=False,
canned_query=table_name,
named_parameters=canned_query.get("params"),
write=bool(canned_query.get("write")),
)
is_view, table_exists = map(
bool,
await gather(db.get_view_definition(table_name),
db.table_exists(table_name)),
)
# If table or view not found, return 404
if not is_view and not table_exists:
raise NotFound(f"Table not found: {table_name}")
# Ensure user has permission to view this table
await self.ds.ensure_permissions(
request.actor,
[
("view-table", (database_name, table_name)),
("view-database", database_name),
"view-instance",
],
)
private = not await self.ds.permission_allowed(
None, "view-table", (database_name, table_name), default=True)
# Handle ?_filter_column and redirect, if present
redirect_params = filters_should_redirect(request.args)
if redirect_params:
return self.redirect(
request,
path_with_added_args(request, redirect_params),
forward_querystring=False,
)
# If ?_sort_by_desc=on (from checkbox) redirect to _sort_desc=(_sort)
if "_sort_by_desc" in request.args:
return self.redirect(
request,
path_with_added_args(
request,
{
"_sort_desc": request.args.get("_sort"),
"_sort_by_desc": None,
"_sort": None,
},
),
forward_querystring=False,
)
# Introspect columns and primary keys for table
pks = await db.primary_keys(table_name)
table_columns = await db.table_columns(table_name)
# Take ?_col= and ?_nocol= into account
specified_columns = await self.columns_to_select(
table_columns, pks, request)
select_specified_columns = ", ".join(
escape_sqlite(t) for t in specified_columns)
select_all_columns = ", ".join(escape_sqlite(t) for t in table_columns)
# rowid tables (no specified primary key) need a different SELECT
use_rowid = not pks and not is_view
if use_rowid:
select_specified_columns = f"rowid, {select_specified_columns}"
select_all_columns = f"rowid, {select_all_columns}"
order_by = "rowid"
order_by_pks = "rowid"
else:
order_by_pks = ", ".join([escape_sqlite(pk) for pk in pks])
order_by = order_by_pks
if is_view:
order_by = ""
nocount = request.args.get("_nocount")
nofacet = request.args.get("_nofacet")
nosuggest = request.args.get("_nosuggest")
if request.args.get("_shape") in ("array", "object"):
nocount = True
nofacet = True
table_metadata = self.ds.table_metadata(database_name, table_name)
units = table_metadata.get("units", {})
# Arguments that start with _ and don't contain a __ are
# special - things like ?_search= - and should not be
# treated as filters.
filter_args = []
for key in request.args:
if not (key.startswith("_") and "__" not in key):
for v in request.args.getlist(key):
filter_args.append((key, v))
# Build where clauses from query string arguments
filters = Filters(sorted(filter_args), units, ureg)
where_clauses, params = filters.build_where_clauses(table_name)
# Execute filters_from_request plugin hooks - including the default
# ones that live in datasette/filters.py
extra_context_from_filters = {}
extra_human_descriptions = []
for hook in pm.hook.filters_from_request(
request=request,
table=table_name,
database=database_name,
datasette=self.ds,
):
filter_arguments = await await_me_maybe(hook)
if filter_arguments:
where_clauses.extend(filter_arguments.where_clauses)
params.update(filter_arguments.params)
extra_human_descriptions.extend(
filter_arguments.human_descriptions)
extra_context_from_filters.update(
filter_arguments.extra_context)
# Deal with custom sort orders
sortable_columns = await self.sortable_columns_for_table(
database_name, table_name, use_rowid)
sort = request.args.get("_sort")
sort_desc = request.args.get("_sort_desc")
if not sort and not sort_desc:
sort = table_metadata.get("sort")
sort_desc = table_metadata.get("sort_desc")
if sort and sort_desc:
raise DatasetteError(
"Cannot use _sort and _sort_desc at the same time")
if sort:
if sort not in sortable_columns:
raise DatasetteError(f"Cannot sort table by {sort}")
order_by = escape_sqlite(sort)
if sort_desc:
if sort_desc not in sortable_columns:
raise DatasetteError(f"Cannot sort table by {sort_desc}")
order_by = f"{escape_sqlite(sort_desc)} desc"
from_sql = "from {table_name} {where}".format(
table_name=escape_sqlite(table_name),
where=("where {} ".format(" and ".join(where_clauses)))
if where_clauses else "",
)
# Copy of params so we can mutate them later:
from_sql_params = dict(**params)
count_sql = f"select count(*) {from_sql}"
# Handle pagination driven by ?_next=
_next = _next or request.args.get("_next")
offset = ""
if _next:
sort_value = None
if is_view:
# _next is an offset
offset = f" offset {int(_next)}"
else:
components = urlsafe_components(_next)
# If a sort order is applied and there are multiple components,
# the first of these is the sort value
if (sort or sort_desc) and (len(components) > 1):
sort_value = components[0]
# Special case for if non-urlencoded first token was $null
if _next.split(",")[0] == "$null":
sort_value = None
components = components[1:]
# Figure out the SQL for next-based-on-primary-key first
next_by_pk_clauses = []
if use_rowid:
next_by_pk_clauses.append(f"rowid > :p{len(params)}")
params[f"p{len(params)}"] = components[0]
else:
# Apply the tie-breaker based on primary keys
if len(components) == len(pks):
param_len = len(params)
next_by_pk_clauses.append(
compound_keys_after_sql(pks, param_len))
for i, pk_value in enumerate(components):
params[f"p{param_len + i}"] = pk_value
# Now add the sort SQL, which may incorporate next_by_pk_clauses
if sort or sort_desc:
if sort_value is None:
if sort_desc:
# Just items where column is null ordered by pk
where_clauses.append(
"({column} is null and {next_clauses})".format(
column=escape_sqlite(sort_desc),
next_clauses=" and ".join(
next_by_pk_clauses),
))
else:
where_clauses.append(
"({column} is not null or ({column} is null and {next_clauses}))"
.format(
column=escape_sqlite(sort),
next_clauses=" and ".join(
next_by_pk_clauses),
))
else:
where_clauses.append(
"({column} {op} :p{p}{extra_desc_only} or ({column} = :p{p} and {next_clauses}))"
.format(
column=escape_sqlite(sort or sort_desc),
op=">" if sort else "<",
p=len(params),
extra_desc_only=""
if sort else " or {column2} is null".format(
column2=escape_sqlite(sort or sort_desc)),
next_clauses=" and ".join(next_by_pk_clauses),
))
params[f"p{len(params)}"] = sort_value
order_by = f"{order_by}, {order_by_pks}"
else:
where_clauses.extend(next_by_pk_clauses)
where_clause = ""
if where_clauses:
where_clause = f"where {' and '.join(where_clauses)} "
if order_by:
order_by = f"order by {order_by}"
extra_args = {}
# Handle ?_size=500
page_size = _size or request.args.get("_size") or table_metadata.get(
"size")
if page_size:
if page_size == "max":
page_size = self.ds.max_returned_rows
try:
page_size = int(page_size)
if page_size < 0:
raise ValueError
except ValueError:
raise BadRequest("_size must be a positive integer")
if page_size > self.ds.max_returned_rows:
raise BadRequest(
f"_size must be <= {self.ds.max_returned_rows}")
extra_args["page_size"] = page_size
else:
page_size = self.ds.page_size
# Facets are calculated against SQL without order by or limit
sql_no_order_no_limit = (
"select {select_all_columns} from {table_name} {where}".format(
select_all_columns=select_all_columns,
table_name=escape_sqlite(table_name),
where=where_clause,
))
# This is the SQL that populates the main table on the page
sql = "select {select_specified_columns} from {table_name} {where}{order_by} limit {page_size}{offset}".format(
select_specified_columns=select_specified_columns,
table_name=escape_sqlite(table_name),
where=where_clause,
order_by=order_by,
page_size=page_size + 1,
offset=offset,
)
if request.args.get("_timelimit"):
extra_args["custom_time_limit"] = int(
request.args.get("_timelimit"))
# Execute the main query!
results = await db.execute(sql, params, truncate=True, **extra_args)
# Calculate the total count for this query
filtered_table_rows_count = None
if (not db.is_mutable and self.ds.inspect_data
and count_sql == f"select count(*) from {table_name} "):
# We can use a previously cached table row count
try:
filtered_table_rows_count = self.ds.inspect_data[
database_name]["tables"][table_name]["count"]
except KeyError:
pass
# Otherwise run a select count(*) ...
if count_sql and filtered_table_rows_count is None and not nocount:
try:
count_rows = list(await db.execute(count_sql, from_sql_params))
filtered_table_rows_count = count_rows[0][0]
except QueryInterrupted:
pass
# Faceting
if not self.ds.setting("allow_facet") and any(
arg.startswith("_facet") for arg in request.args):
raise BadRequest("_facet= is not allowed")
# pylint: disable=no-member
facet_classes = list(
itertools.chain.from_iterable(pm.hook.register_facet_classes()))
facet_results = {}
facets_timed_out = []
facet_instances = []
for klass in facet_classes:
facet_instances.append(
klass(
self.ds,
request,
database_name,
sql=sql_no_order_no_limit,
params=params,
table=table_name,
metadata=table_metadata,
row_count=filtered_table_rows_count,
))
async def execute_facets():
if not nofacet:
# Run them in parallel
facet_awaitables = [
facet.facet_results() for facet in facet_instances
]
facet_awaitable_results = await gather(*facet_awaitables)
for (
instance_facet_results,
instance_facets_timed_out,
) in facet_awaitable_results:
for facet_info in instance_facet_results:
base_key = facet_info["name"]
key = base_key
i = 1
while key in facet_results:
i += 1
key = f"{base_key}_{i}"
facet_results[key] = facet_info
facets_timed_out.extend(instance_facets_timed_out)
suggested_facets = []
async def execute_suggested_facets():
# Calculate suggested facets
if (self.ds.setting("suggest_facets")
and self.ds.setting("allow_facet") and not _next
and not nofacet and not nosuggest):
# Run them in parallel
facet_suggest_awaitables = [
facet.suggest() for facet in facet_instances
]
for suggest_result in await gather(*facet_suggest_awaitables):
suggested_facets.extend(suggest_result)
await gather(execute_facets(), execute_suggested_facets())
# Figure out columns and rows for the query
columns = [r[0] for r in results.description]
rows = list(results.rows)
# Expand labeled columns if requested
expanded_columns = []
expandable_columns = await self.expandable_columns(
database_name, table_name)
columns_to_expand = None
try:
all_labels = value_as_boolean(request.args.get("_labels", ""))
except ValueError:
all_labels = default_labels
# Check for explicit _label=
if "_label" in request.args:
columns_to_expand = request.args.getlist("_label")
if columns_to_expand is None and all_labels:
# expand all columns with foreign keys
columns_to_expand = [fk["column"] for fk, _ in expandable_columns]
if columns_to_expand:
expanded_labels = {}
for fk, _ in expandable_columns:
column = fk["column"]
if column not in columns_to_expand:
continue
if column not in columns:
continue
expanded_columns.append(column)
# Gather the values
column_index = columns.index(column)
values = [row[column_index] for row in rows]
# Expand them
expanded_labels.update(await self.ds.expand_foreign_keys(
database_name, table_name, column, values))
if expanded_labels:
# Rewrite the rows
new_rows = []
for row in rows:
new_row = CustomRow(columns)
for column in row.keys():
value = row[column]
if (column, value
) in expanded_labels and value is not None:
new_row[column] = {
"value": value,
"label": expanded_labels[(column, value)],
}
else:
new_row[column] = value
new_rows.append(new_row)
rows = new_rows
# Pagination next link
next_value = None
next_url = None
if 0 < page_size < len(rows):
if is_view:
next_value = int(_next or 0) + page_size
else:
next_value = path_from_row_pks(rows[-2], pks, use_rowid)
# If there's a sort or sort_desc, add that value as a prefix
if (sort or sort_desc) and not is_view:
prefix = rows[-2][sort or sort_desc]
if isinstance(prefix, dict) and "value" in prefix:
prefix = prefix["value"]
if prefix is None:
prefix = "$null"
else:
prefix = tilde_encode(str(prefix))
next_value = f"{prefix},{next_value}"
added_args = {"_next": next_value}
if sort:
added_args["_sort"] = sort
else:
added_args["_sort_desc"] = sort_desc
else:
added_args = {"_next": next_value}
next_url = self.ds.absolute_url(
request,
self.ds.urls.path(path_with_replaced_args(request,
added_args)))
rows = rows[:page_size]
# human_description_en combines filters AND search, if provided
human_description_en = filters.human_description_en(
extra=extra_human_descriptions)
if sort or sort_desc:
sorted_by = "sorted by {}{}".format(
(sort or sort_desc), " descending" if sort_desc else "")
human_description_en = " ".join(
[b for b in [human_description_en, sorted_by] if b])
async def extra_template():
nonlocal sort
display_columns, display_rows = await display_columns_and_rows(
self.ds,
database_name,
table_name,
results.description,
rows,
link_column=not is_view,
truncate_cells=self.ds.setting("truncate_cells_html"),
sortable_columns=await
self.sortable_columns_for_table(database_name,
table_name,
use_rowid=True),
)
metadata = ((self.ds.metadata("databases")
or {}).get(database_name,
{}).get("tables", {}).get(table_name, {}))
self.ds.update_with_inherited_metadata(metadata)
form_hidden_args = []
for key in request.args:
if (key.startswith("_")
and key not in ("_sort", "_search", "_next")
and "__" not in key):
for value in request.args.getlist(key):
form_hidden_args.append((key, value))
# if no sort specified AND table has a single primary key,
# set sort to that so arrow is displayed
if not sort and not sort_desc:
if 1 == len(pks):
sort = pks[0]
elif use_rowid:
sort = "rowid"
async def table_actions():
links = []
for hook in pm.hook.table_actions(
datasette=self.ds,
table=table_name,
database=database_name,
actor=request.actor,
request=request,
):
extra_links = await await_me_maybe(hook)
if extra_links:
links.extend(extra_links)
return links
# filter_columns combine the columns we know are available
# in the table with any additional columns (such as rowid)
# which are available in the query
filter_columns = list(columns) + [
table_column for table_column in table_columns
if table_column not in columns
]
d = {
"table_actions":
table_actions,
"use_rowid":
use_rowid,
"filters":
filters,
"display_columns":
display_columns,
"filter_columns":
filter_columns,
"display_rows":
display_rows,
"facets_timed_out":
facets_timed_out,
"sorted_facet_results":
sorted(
facet_results.values(),
key=lambda f: (len(f["results"]), f["name"]),
reverse=True,
),
"form_hidden_args":
form_hidden_args,
"is_sortable":
any(c["sortable"] for c in display_columns),
"fix_path":
self.ds.urls.path,
"path_with_replaced_args":
path_with_replaced_args,
"path_with_removed_args":
path_with_removed_args,
"append_querystring":
append_querystring,
"request":
request,
"sort":
sort,
"sort_desc":
sort_desc,
"disable_sort":
is_view,
"custom_table_templates": [
f"_table-{to_css_class(database_name)}-{to_css_class(table_name)}.html",
f"_table-table-{to_css_class(database_name)}-{to_css_class(table_name)}.html",
"_table.html",
],
"metadata":
metadata,
"view_definition":
await db.get_view_definition(table_name),
"table_definition":
await db.get_table_definition(table_name),
"datasette_allow_facet":
"true" if self.ds.setting("allow_facet") else "false",
}
d.update(extra_context_from_filters)
return d
return (
{
"database":
database_name,
"table":
table_name,
"is_view":
is_view,
"human_description_en":
human_description_en,
"rows":
rows[:page_size],
"truncated":
results.truncated,
"filtered_table_rows_count":
filtered_table_rows_count,
"expanded_columns":
expanded_columns,
"expandable_columns":
expandable_columns,
"columns":
columns,
"primary_keys":
pks,
"units":
units,
"query": {
"sql": sql,
"params": params
},
"facet_results":
facet_results,
"suggested_facets":
suggested_facets,
"next":
next_value and str(next_value) or None,
"next_url":
next_url,
"private":
private,
"allow_execute_sql":
await self.ds.permission_allowed(request.actor,
"execute-sql",
database_name,
default=True),
},
extra_template,
(
f"table-{to_css_class(database_name)}-{to_css_class(table_name)}.html",
"table.html",
),
)
async def data(self, request, name, hash, table, default_labels=False, _next=None, _size=None):
canned_query = self.ds.get_canned_query(name, table)
if canned_query is not None:
return await self.custom_sql(
request,
name,
hash,
canned_query["sql"],
editable=False,
canned_query=table,
)
is_view = bool(await self.ds.get_view_definition(name, table))
info = self.ds.inspect()
table_info = info[name]["tables"].get(table) or {}
if not is_view and not table_info:
raise NotFound("Table not found: {}".format(table))
pks = table_info.get("primary_keys") or []
use_rowid = not pks and not is_view
if use_rowid:
select = "rowid, *"
order_by = "rowid"
order_by_pks = "rowid"
else:
select = "*"
order_by_pks = ", ".join([escape_sqlite(pk) for pk in pks])
order_by = order_by_pks
if is_view:
order_by = ""
# We roll our own query_string decoder because by default Sanic
# drops anything with an empty value e.g. ?name__exact=
args = RequestParameters(
urllib.parse.parse_qs(request.query_string, keep_blank_values=True)
)
# Special args start with _ and do not contain a __
# That's so if there is a column that starts with _
# it can still be queried using ?_col__exact=blah
special_args = {}
special_args_lists = {}
other_args = {}
for key, value in args.items():
if key.startswith("_") and "__" not in key:
special_args[key] = value[0]
special_args_lists[key] = value
else:
other_args[key] = value[0]
# Handle ?_filter_column and redirect, if present
redirect_params = filters_should_redirect(special_args)
if redirect_params:
return self.redirect(
request,
path_with_added_args(request, redirect_params),
forward_querystring=False,
)
# Spot ?_sort_by_desc and redirect to _sort_desc=(_sort)
if "_sort_by_desc" in special_args:
return self.redirect(
request,
path_with_added_args(
request,
{
"_sort_desc": special_args.get("_sort"),
"_sort_by_desc": None,
"_sort": None,
},
),
forward_querystring=False,
)
table_metadata = self.table_metadata(name, table)
units = table_metadata.get("units", {})
filters = Filters(sorted(other_args.items()), units, ureg)
where_clauses, params = filters.build_where_clauses()
# _search support:
fts_table = info[name]["tables"].get(table, {}).get("fts_table")
search_args = dict(
pair for pair in special_args.items() if pair[0].startswith("_search")
)
search_descriptions = []
search = ""
if fts_table and search_args:
if "_search" in search_args:
# Simple ?_search=xxx
search = search_args["_search"]
where_clauses.append(
"rowid in (select rowid from {fts_table} where {fts_table} match :search)".format(
fts_table=escape_sqlite(fts_table),
)
)
search_descriptions.append('search matches "{}"'.format(search))
params["search"] = search
else:
# More complex: search against specific columns
valid_columns = set(info[name]["tables"][fts_table]["columns"])
for i, (key, search_text) in enumerate(search_args.items()):
search_col = key.split("_search_", 1)[1]
if search_col not in valid_columns:
raise DatasetteError("Cannot search by that column", status=400)
where_clauses.append(
"rowid in (select rowid from {fts_table} where {search_col} match :search_{i})".format(
fts_table=escape_sqlite(fts_table),
search_col=escape_sqlite(search_col),
i=i
)
)
search_descriptions.append(
'search column "{}" matches "{}"'.format(
search_col, search_text
)
)
params["search_{}".format(i)] = search_text
table_rows_count = None
sortable_columns = set()
if not is_view:
table_rows_count = table_info["count"]
sortable_columns = self.sortable_columns_for_table(name, table, use_rowid)
# Allow for custom sort order
sort = special_args.get("_sort")
if sort:
if sort not in sortable_columns:
raise DatasetteError("Cannot sort table by {}".format(sort))
order_by = escape_sqlite(sort)
sort_desc = special_args.get("_sort_desc")
if sort_desc:
if sort_desc not in sortable_columns:
raise DatasetteError("Cannot sort table by {}".format(sort_desc))
if sort:
raise DatasetteError("Cannot use _sort and _sort_desc at the same time")
order_by = "{} desc".format(escape_sqlite(sort_desc))
from_sql = "from {table_name} {where}".format(
table_name=escape_sqlite(table),
where=(
"where {} ".format(" and ".join(where_clauses))
) if where_clauses else "",
)
# Store current params and where_clauses for later:
from_sql_params = dict(**params)
from_sql_where_clauses = where_clauses[:]
count_sql = "select count(*) {}".format(from_sql)
_next = _next or special_args.get("_next")
offset = ""
if _next:
if is_view:
# _next is an offset
offset = " offset {}".format(int(_next))
else:
components = urlsafe_components(_next)
# If a sort order is applied, the first of these is the sort value
if sort or sort_desc:
sort_value = components[0]
# Special case for if non-urlencoded first token was $null
if _next.split(",")[0] == "$null":
sort_value = None
components = components[1:]
# Figure out the SQL for next-based-on-primary-key first
next_by_pk_clauses = []
if use_rowid:
next_by_pk_clauses.append("rowid > :p{}".format(len(params)))
params["p{}".format(len(params))] = components[0]
else:
# Apply the tie-breaker based on primary keys
if len(components) == len(pks):
param_len = len(params)
next_by_pk_clauses.append(
compound_keys_after_sql(pks, param_len)
)
for i, pk_value in enumerate(components):
params["p{}".format(param_len + i)] = pk_value
# Now add the sort SQL, which may incorporate next_by_pk_clauses
if sort or sort_desc:
if sort_value is None:
if sort_desc:
# Just items where column is null ordered by pk
where_clauses.append(
"({column} is null and {next_clauses})".format(
column=escape_sqlite(sort_desc),
next_clauses=" and ".join(next_by_pk_clauses),
)
)
else:
where_clauses.append(
"({column} is not null or ({column} is null and {next_clauses}))".format(
column=escape_sqlite(sort),
next_clauses=" and ".join(next_by_pk_clauses),
)
)
else:
where_clauses.append(
"({column} {op} :p{p}{extra_desc_only} or ({column} = :p{p} and {next_clauses}))".format(
column=escape_sqlite(sort or sort_desc),
op=">" if sort else "<",
p=len(params),
extra_desc_only="" if sort else " or {column2} is null".format(
column2=escape_sqlite(sort or sort_desc)
),
next_clauses=" and ".join(next_by_pk_clauses),
)
)
params["p{}".format(len(params))] = sort_value
order_by = "{}, {}".format(order_by, order_by_pks)
else:
where_clauses.extend(next_by_pk_clauses)
where_clause = ""
if where_clauses:
where_clause = "where {} ".format(" and ".join(where_clauses))
if order_by:
order_by = "order by {} ".format(order_by)
# _group_count=col1&_group_count=col2
group_count = special_args_lists.get("_group_count") or []
if group_count:
sql = 'select {group_cols}, count(*) as "count" from {table_name} {where} group by {group_cols} order by "count" desc limit 100'.format(
group_cols=", ".join(
'"{}"'.format(group_count_col) for group_count_col in group_count
),
table_name=escape_sqlite(table),
where=where_clause,
)
return await self.custom_sql(request, name, hash, sql, editable=True)
extra_args = {}
# Handle ?_size=500
page_size = _size or request.raw_args.get("_size")
if page_size:
if page_size == "max":
page_size = self.max_returned_rows
try:
page_size = int(page_size)
if page_size < 0:
raise ValueError
except ValueError:
raise DatasetteError("_size must be a positive integer", status=400)
if page_size > self.max_returned_rows:
raise DatasetteError(
"_size must be <= {}".format(self.max_returned_rows), status=400
)
extra_args["page_size"] = page_size
else:
page_size = self.page_size
sql = "select {select} from {table_name} {where}{order_by}limit {limit}{offset}".format(
select=select,
table_name=escape_sqlite(table),
where=where_clause,
order_by=order_by,
limit=page_size + 1,
offset=offset,
)
if request.raw_args.get("_timelimit"):
extra_args["custom_time_limit"] = int(request.raw_args["_timelimit"])
results = await self.ds.execute(
name, sql, params, truncate=True, **extra_args
)
# facets support
facet_size = self.ds.config["default_facet_size"]
metadata_facets = table_metadata.get("facets", [])
facets = metadata_facets[:]
if request.args.get("_facet") and not self.ds.config["allow_facet"]:
raise DatasetteError("_facet= is not allowed", status=400)
try:
facets.extend(request.args["_facet"])
except KeyError:
pass
facet_results = {}
facets_timed_out = []
for column in facets:
if _next:
continue
facet_sql = """
select {col} as value, count(*) as count
{from_sql} {and_or_where} {col} is not null
group by {col} order by count desc limit {limit}
""".format(
col=escape_sqlite(column),
from_sql=from_sql,
and_or_where='and' if from_sql_where_clauses else 'where',
limit=facet_size+1,
)
try:
facet_rows_results = await self.ds.execute(
name, facet_sql, params,
truncate=False,
custom_time_limit=self.ds.config["facet_time_limit_ms"],
)
facet_results_values = []
facet_results[column] = {
"name": column,
"results": facet_results_values,
"truncated": len(facet_rows_results) > facet_size,
}
facet_rows = facet_rows_results.rows[:facet_size]
# Attempt to expand foreign keys into labels
values = [row["value"] for row in facet_rows]
expanded = (await self.expand_foreign_keys(
name, table, column, values
))
for row in facet_rows:
selected = str(other_args.get(column)) == str(row["value"])
if selected:
toggle_path = path_with_removed_args(
request, {column: str(row["value"])}
)
else:
toggle_path = path_with_added_args(
request, {column: row["value"]}
)
facet_results_values.append({
"value": row["value"],
"label": expanded.get(
(column, row["value"]),
row["value"]
),
"count": row["count"],
"toggle_url": urllib.parse.urljoin(
request.url, toggle_path
),
"selected": selected,
})
except InterruptedError:
facets_timed_out.append(column)
columns = [r[0] for r in results.description]
rows = list(results.rows)
filter_columns = columns[:]
if use_rowid and filter_columns[0] == "rowid":
filter_columns = filter_columns[1:]
# Expand labeled columns if requested
expanded_columns = []
expandable_columns = self.expandable_columns(name, table)
columns_to_expand = None
try:
all_labels = value_as_boolean(special_args.get("_labels", ""))
except ValueError:
all_labels = default_labels
# Check for explicit _label=
if "_label" in request.args:
columns_to_expand = request.args["_label"]
if columns_to_expand is None and all_labels:
# expand all columns with foreign keys
columns_to_expand = [
fk["column"] for fk, _ in expandable_columns
]
if columns_to_expand:
expanded_labels = {}
for fk, label_column in expandable_columns:
column = fk["column"]
if column not in columns_to_expand:
continue
expanded_columns.append(column)
# Gather the values
column_index = columns.index(column)
values = [row[column_index] for row in rows]
# Expand them
expanded_labels.update(await self.expand_foreign_keys(
name, table, column, values
))
if expanded_labels:
# Rewrite the rows
new_rows = []
for row in rows:
new_row = CustomRow(columns)
for column in row.keys():
value = row[column]
if (column, value) in expanded_labels:
new_row[column] = {
'value': value,
'label': expanded_labels[(column, value)]
}
else:
new_row[column] = value
new_rows.append(new_row)
rows = new_rows
# Pagination next link
next_value = None
next_url = None
if len(rows) > page_size and page_size > 0:
if is_view:
next_value = int(_next or 0) + page_size
else:
next_value = path_from_row_pks(rows[-2], pks, use_rowid)
# If there's a sort or sort_desc, add that value as a prefix
if (sort or sort_desc) and not is_view:
prefix = rows[-2][sort or sort_desc]
if prefix is None:
prefix = "$null"
else:
prefix = urllib.parse.quote_plus(str(prefix))
next_value = "{},{}".format(prefix, next_value)
added_args = {"_next": next_value}
if sort:
added_args["_sort"] = sort
else:
added_args["_sort_desc"] = sort_desc
else:
added_args = {"_next": next_value}
next_url = urllib.parse.urljoin(
request.url, path_with_replaced_args(request, added_args)
)
rows = rows[:page_size]
# Number of filtered rows in whole set:
filtered_table_rows_count = None
if count_sql:
try:
count_rows = list(await self.ds.execute(
name, count_sql, from_sql_params
))
filtered_table_rows_count = count_rows[0][0]
except InterruptedError:
pass
# Detect suggested facets
suggested_facets = []
if self.ds.config["suggest_facets"] and self.ds.config["allow_facet"]:
for facet_column in columns:
if facet_column in facets:
continue
if _next:
continue
if not self.ds.config["suggest_facets"]:
continue
suggested_facet_sql = '''
select distinct {column} {from_sql}
{and_or_where} {column} is not null
limit {limit}
'''.format(
column=escape_sqlite(facet_column),
from_sql=from_sql,
and_or_where='and' if from_sql_where_clauses else 'where',
limit=facet_size+1
)
distinct_values = None
try:
distinct_values = await self.ds.execute(
name, suggested_facet_sql, from_sql_params,
truncate=False,
custom_time_limit=self.ds.config["facet_suggest_time_limit_ms"],
)
num_distinct_values = len(distinct_values)
if (
num_distinct_values and
num_distinct_values > 1 and
num_distinct_values <= facet_size and
num_distinct_values < filtered_table_rows_count
):
suggested_facets.append({
'name': facet_column,
'toggle_url': path_with_added_args(
request, {'_facet': facet_column}
),
})
except InterruptedError:
pass
# human_description_en combines filters AND search, if provided
human_description_en = filters.human_description_en(extra=search_descriptions)
if sort or sort_desc:
sorted_by = "sorted by {}{}".format(
(sort or sort_desc), " descending" if sort_desc else ""
)
human_description_en = " ".join(
[b for b in [human_description_en, sorted_by] if b]
)
async def extra_template():
display_columns, display_rows = await self.display_columns_and_rows(
name,
table,
results.description,
rows,
link_column=not is_view,
)
metadata = self.ds.metadata.get("databases", {}).get(name, {}).get(
"tables", {}
).get(
table, {}
)
self.ds.update_with_inherited_metadata(metadata)
return {
"database_hash": hash,
"supports_search": bool(fts_table),
"search": search or "",
"use_rowid": use_rowid,
"filters": filters,
"display_columns": display_columns,
"filter_columns": filter_columns,
"display_rows": display_rows,
"facets_timed_out": facets_timed_out,
"sorted_facet_results": sorted(
facet_results.values(),
key=lambda f: (len(f["results"]), f["name"]),
reverse=True
),
"facet_hideable": lambda facet: facet not in metadata_facets,
"is_sortable": any(c["sortable"] for c in display_columns),
"path_with_replaced_args": path_with_replaced_args,
"path_with_removed_args": path_with_removed_args,
"append_querystring": append_querystring,
"request": request,
"sort": sort,
"sort_desc": sort_desc,
"disable_sort": is_view,
"custom_rows_and_columns_templates": [
"_rows_and_columns-{}-{}.html".format(
to_css_class(name), to_css_class(table)
),
"_rows_and_columns-table-{}-{}.html".format(
to_css_class(name), to_css_class(table)
),
"_rows_and_columns.html",
],
"metadata": metadata,
"view_definition": await self.ds.get_view_definition(name, table),
"table_definition": await self.ds.get_table_definition(name, table),
}
return {
"database": name,
"table": table,
"is_view": is_view,
"human_description_en": human_description_en,
"rows": rows[:page_size],
"truncated": results.truncated,
"table_rows_count": table_rows_count,
"filtered_table_rows_count": filtered_table_rows_count,
"expanded_columns": expanded_columns,
"expandable_columns": expandable_columns,
"columns": columns,
"primary_keys": pks,
"units": units,
"query": {"sql": sql, "params": params},
"facet_results": facet_results,
"suggested_facets": suggested_facets,
"next": next_value and str(next_value) or None,
"next_url": next_url,
}, extra_template, (
"table-{}-{}.html".format(to_css_class(name), to_css_class(table)),
"table.html",
)
async def display_columns_and_rows(
self,
database,
table,
description,
rows,
link_column=False,
):
"Returns columns, rows for specified table - including fancy foreign key treatment"
table_metadata = self.table_metadata(database, table)
info = self.ds.inspect()[database]
sortable_columns = self.sortable_columns_for_table(database, table, True)
columns = [
{"name": r[0], "sortable": r[0] in sortable_columns} for r in description
]
tables = info["tables"]
table_info = tables.get(table) or {}
pks = table_info.get("primary_keys") or []
column_to_foreign_key_table = {
fk["column"]: fk["other_table"]
for fk in table_info.get(
"foreign_keys", {}
).get("outgoing", None) or []
}
cell_rows = []
for row in rows:
cells = []
# Unless we are a view, the first column is a link - either to the rowid
# or to the simple or compound primary key
if link_column:
cells.append(
{
"column": pks[0] if len(pks) == 1 else "Link",
"value": jinja2.Markup(
'<a href="/{database}/{table}/{flat_pks_quoted}">{flat_pks}</a>'.format(
database=database,
table=urllib.parse.quote_plus(table),
flat_pks=str(
jinja2.escape(
path_from_row_pks(row, pks, not pks, False)
)
),
flat_pks_quoted=path_from_row_pks(row, pks, not pks),
)
),
}
)
for value, column_dict in zip(row, columns):
column = column_dict["name"]
if link_column and len(pks) == 1 and column == pks[0]:
# If there's a simple primary key, don't repeat the value as it's
# already shown in the link column.
continue
if isinstance(value, dict):
# It's an expanded foreign key - display link to other row
label = value["label"]
value = value["value"]
# The table we link to depends on the column
other_table = column_to_foreign_key_table[column]
link_template = (
LINK_WITH_LABEL if (label != value) else LINK_WITH_VALUE
)
display_value = jinja2.Markup(link_template.format(
database=database,
table=urllib.parse.quote_plus(other_table),
link_id=urllib.parse.quote_plus(str(value)),
id=str(jinja2.escape(value)),
label=str(jinja2.escape(label)),
))
elif value in ("", None):
display_value = jinja2.Markup(" ")
elif is_url(str(value).strip()):
display_value = jinja2.Markup(
'<a href="{url}">{url}</a>'.format(
url=jinja2.escape(value.strip())
)
)
elif column in table_metadata.get("units", {}) and value != "":
# Interpret units using pint
value = value * ureg(table_metadata["units"][column])
# Pint uses floating point which sometimes introduces errors in the compact
# representation, which we have to round off to avoid ugliness. In the vast
# majority of cases this rounding will be inconsequential. I hope.
value = round(value.to_compact(), 6)
display_value = jinja2.Markup(
"{:~P}".format(value).replace(" ", " ")
)
else:
display_value = str(value)
cells.append({"column": column, "value": display_value})
cell_rows.append(cells)
if link_column:
# Add the link column header.
# If it's a simple primary key, we have to remove and re-add that column name at
# the beginning of the header row.
if len(pks) == 1:
columns = [col for col in columns if col["name"] != pks[0]]
columns = [
{"name": pks[0] if len(pks) == 1 else "Link", "sortable": len(pks) == 1}
] + columns
return columns, cell_rows
async def display_columns_and_rows(
self,
database,
table,
description,
rows,
link_column=False,
expand_foreign_keys=True,
):
"Returns columns, rows for specified table - including fancy foreign key treatment"
table_metadata = self.table_metadata(database, table)
info = self.ds.inspect()[database]
sortable_columns = self.sortable_columns_for_table(
database, table, True)
columns = [{
"name": r[0],
"sortable": r[0] in sortable_columns
} for r in description]
tables = info["tables"]
table_info = tables.get(table) or {}
pks = table_info.get("primary_keys") or []
# Prefetch foreign key resolutions for later expansion:
fks = {}
labeled_fks = {}
if table_info and expand_foreign_keys:
foreign_keys = table_info["foreign_keys"]["outgoing"]
for fk in foreign_keys:
label_column = (
# First look in metadata.json definition for this foreign key table:
self.table_metadata(database,
fk["other_table"]).get("label_column")
# Fall back to label_column from .inspect() detection:
or tables.get(fk["other_table"], {}).get("label_column"))
if not label_column:
# No label for this FK
fks[fk["column"]] = fk["other_table"]
continue
ids_to_lookup = set([row[fk["column"]] for row in rows])
sql = '''
select {other_column}, {label_column}
from {other_table}
where {other_column} in ({placeholders})
'''.format(
other_column=escape_sqlite(fk["other_column"]),
label_column=escape_sqlite(label_column),
other_table=escape_sqlite(fk["other_table"]),
placeholders=", ".join(["?"] * len(ids_to_lookup)),
)
try:
results = await self.execute(database, sql,
list(set(ids_to_lookup)))
except InterruptedError:
pass
else:
for id, value in results:
labeled_fks[(fk["column"], id)] = (fk["other_table"],
value)
cell_rows = []
for row in rows:
cells = []
# Unless we are a view, the first column is a link - either to the rowid
# or to the simple or compound primary key
if link_column:
cells.append({
"column":
pks[0] if len(pks) == 1 else "Link",
"value":
jinja2.Markup(
'<a href="/{database}/{table}/{flat_pks_quoted}">{flat_pks}</a>'
.format(
database=database,
table=urllib.parse.quote_plus(table),
flat_pks=str(
jinja2.escape(
path_from_row_pks(row, pks, not pks,
False))),
flat_pks_quoted=path_from_row_pks(
row, pks, not pks),
)),
})
for value, column_dict in zip(row, columns):
column = column_dict["name"]
if link_column and len(pks) == 1 and column == pks[0]:
# If there's a simple primary key, don't repeat the value as it's
# already shown in the link column.
continue
if (column, value) in labeled_fks:
other_table, label = labeled_fks[(column, value)]
display_value = jinja2.Markup(
'<a href="/{database}/{table}/{link_id}">{label}</a> <em>{id}</em>'
.format(
database=database,
table=urllib.parse.quote_plus(other_table),
link_id=urllib.parse.quote_plus(str(value)),
id=str(jinja2.escape(value)),
label=str(jinja2.escape(label)),
))
elif column in fks:
display_value = jinja2.Markup(
'<a href="/{database}/{table}/{link_id}">{id}</a>'.
format(
database=database,
table=urllib.parse.quote_plus(fks[column]),
link_id=urllib.parse.quote_plus(str(value)),
id=str(jinja2.escape(value)),
))
elif value is None:
display_value = jinja2.Markup(" ")
elif is_url(str(value).strip()):
display_value = jinja2.Markup(
'<a href="{url}">{url}</a>'.format(
url=jinja2.escape(value.strip())))
elif column in table_metadata.get("units", {}) and value != "":
# Interpret units using pint
value = value * ureg(table_metadata["units"][column])
# Pint uses floating point which sometimes introduces errors in the compact
# representation, which we have to round off to avoid ugliness. In the vast
# majority of cases this rounding will be inconsequential. I hope.
value = round(value.to_compact(), 6)
display_value = jinja2.Markup(
"{:~P}".format(value).replace(" ", " "))
else:
display_value = str(value)
cells.append({"column": column, "value": display_value})
cell_rows.append(cells)
if link_column:
# Add the link column header.
# If it's a simple primary key, we have to remove and re-add that column name at
# the beginning of the header row.
if len(pks) == 1:
columns = [col for col in columns if col["name"] != pks[0]]
columns = [{
"name": pks[0] if len(pks) == 1 else "Link",
"sortable": len(pks) == 1
}] + columns
return columns, cell_rows
async def data(self, request, name, hash, table):
table = urllib.parse.unquote_plus(table)
canned_query = self.ds.get_canned_query(name, table)
if canned_query is not None:
return await self.custom_sql(
request,
name,
hash,
canned_query["sql"],
editable=False,
canned_query=table,
)
is_view = bool(
list(await self.execute(
name,
"SELECT count(*) from sqlite_master WHERE type = 'view' and name=:n",
{"n": table},
))[0][0])
view_definition = None
table_definition = None
if is_view:
view_definition = list(await self.execute(
name,
'select sql from sqlite_master where name = :n and type="view"',
{"n": table},
))[0][0]
else:
table_definition_rows = list(await self.execute(
name,
'select sql from sqlite_master where name = :n and type="table"',
{"n": table},
))
if not table_definition_rows:
raise NotFound("Table not found: {}".format(table))
table_definition = table_definition_rows[0][0]
info = self.ds.inspect()
table_info = info[name]["tables"].get(table) or {}
pks = table_info.get("primary_keys") or []
use_rowid = not pks and not is_view
if use_rowid:
select = "rowid, *"
order_by = "rowid"
order_by_pks = "rowid"
else:
select = "*"
order_by_pks = ", ".join([escape_sqlite(pk) for pk in pks])
order_by = order_by_pks
if is_view:
order_by = ""
# We roll our own query_string decoder because by default Sanic
# drops anything with an empty value e.g. ?name__exact=
args = RequestParameters(
urllib.parse.parse_qs(request.query_string,
keep_blank_values=True))
# Special args start with _ and do not contain a __
# That's so if there is a column that starts with _
# it can still be queried using ?_col__exact=blah
special_args = {}
special_args_lists = {}
other_args = {}
for key, value in args.items():
if key.startswith("_") and "__" not in key:
special_args[key] = value[0]
special_args_lists[key] = value
else:
other_args[key] = value[0]
# Handle ?_filter_column and redirect, if present
redirect_params = filters_should_redirect(special_args)
if redirect_params:
return self.redirect(
request,
path_with_added_args(request, redirect_params),
forward_querystring=False,
)
# Spot ?_sort_by_desc and redirect to _sort_desc=(_sort)
if "_sort_by_desc" in special_args:
return self.redirect(
request,
path_with_added_args(
request,
{
"_sort_desc": special_args.get("_sort"),
"_sort_by_desc": None,
"_sort": None,
},
),
forward_querystring=False,
)
table_metadata = self.table_metadata(name, table)
units = table_metadata.get("units", {})
filters = Filters(sorted(other_args.items()), units, ureg)
where_clauses, params = filters.build_where_clauses()
# _search support:
fts_table = info[name]["tables"].get(table, {}).get("fts_table")
search_args = dict(pair for pair in special_args.items()
if pair[0].startswith("_search"))
search_descriptions = []
search = ""
if fts_table and search_args:
if "_search" in search_args:
# Simple ?_search=xxx
search = search_args["_search"]
where_clauses.append(
"rowid in (select rowid from [{fts_table}] where [{fts_table}] match :search)"
.format(fts_table=fts_table))
search_descriptions.append(
'search matches "{}"'.format(search))
params["search"] = search
else:
# More complex: search against specific columns
valid_columns = set(info[name]["tables"][fts_table]["columns"])
for i, (key, search_text) in enumerate(search_args.items()):
search_col = key.split("_search_", 1)[1]
if search_col not in valid_columns:
raise DatasetteError("Cannot search by that column",
status=400)
where_clauses.append(
"rowid in (select rowid from [{fts_table}] where [{search_col}] match :search_{i})"
.format(fts_table=fts_table,
search_col=search_col,
i=i))
search_descriptions.append(
'search column "{}" matches "{}"'.format(
search_col, search_text))
params["search_{}".format(i)] = search_text
table_rows_count = None
sortable_columns = set()
if not is_view:
table_rows_count = table_info["count"]
sortable_columns = self.sortable_columns_for_table(
name, table, use_rowid)
# Allow for custom sort order
sort = special_args.get("_sort")
if sort:
if sort not in sortable_columns:
raise DatasetteError("Cannot sort table by {}".format(sort))
order_by = escape_sqlite(sort)
sort_desc = special_args.get("_sort_desc")
if sort_desc:
if sort_desc not in sortable_columns:
raise DatasetteError(
"Cannot sort table by {}".format(sort_desc))
if sort:
raise DatasetteError(
"Cannot use _sort and _sort_desc at the same time")
order_by = "{} desc".format(escape_sqlite(sort_desc))
from_sql = "from {table_name} {where}".format(
table_name=escape_sqlite(table),
where=("where {} ".format(" and ".join(where_clauses)))
if where_clauses else "",
)
count_sql = "select count(*) {}".format(from_sql)
_next = special_args.get("_next")
offset = ""
if _next:
if is_view:
# _next is an offset
offset = " offset {}".format(int(_next))
else:
components = urlsafe_components(_next)
# If a sort order is applied, the first of these is the sort value
if sort or sort_desc:
sort_value = components[0]
# Special case for if non-urlencoded first token was $null
if _next.split(",")[0] == "$null":
sort_value = None
components = components[1:]
# Figure out the SQL for next-based-on-primary-key first
next_by_pk_clauses = []
if use_rowid:
next_by_pk_clauses.append("rowid > :p{}".format(
len(params)))
params["p{}".format(len(params))] = components[0]
else:
# Apply the tie-breaker based on primary keys
if len(components) == len(pks):
param_len = len(params)
next_by_pk_clauses.append(
compound_keys_after_sql(pks, param_len))
for i, pk_value in enumerate(components):
params["p{}".format(param_len + i)] = pk_value
# Now add the sort SQL, which may incorporate next_by_pk_clauses
if sort or sort_desc:
if sort_value is None:
if sort_desc:
# Just items where column is null ordered by pk
where_clauses.append(
"({column} is null and {next_clauses})".format(
column=escape_sqlite(sort_desc),
next_clauses=" and ".join(
next_by_pk_clauses),
))
else:
where_clauses.append(
"({column} is not null or ({column} is null and {next_clauses}))"
.format(
column=escape_sqlite(sort),
next_clauses=" and ".join(
next_by_pk_clauses),
))
else:
where_clauses.append(
"({column} {op} :p{p}{extra_desc_only} or ({column} = :p{p} and {next_clauses}))"
.format(
column=escape_sqlite(sort or sort_desc),
op=">" if sort else "<",
p=len(params),
extra_desc_only=""
if sort else " or {column2} is null".format(
column2=escape_sqlite(sort or sort_desc)),
next_clauses=" and ".join(next_by_pk_clauses),
))
params["p{}".format(len(params))] = sort_value
order_by = "{}, {}".format(order_by, order_by_pks)
else:
where_clauses.extend(next_by_pk_clauses)
where_clause = ""
if where_clauses:
where_clause = "where {} ".format(" and ".join(where_clauses))
if order_by:
order_by = "order by {} ".format(order_by)
# _group_count=col1&_group_count=col2
group_count = special_args_lists.get("_group_count") or []
if group_count:
sql = 'select {group_cols}, count(*) as "count" from {table_name} {where} group by {group_cols} order by "count" desc limit 100'.format(
group_cols=", ".join('"{}"'.format(group_count_col)
for group_count_col in group_count),
table_name=escape_sqlite(table),
where=where_clause,
)
return await self.custom_sql(request,
name,
hash,
sql,
editable=True)
extra_args = {}
# Handle ?_page_size=500
page_size = request.raw_args.get("_size")
if page_size:
if page_size == "max":
page_size = self.max_returned_rows
try:
page_size = int(page_size)
if page_size < 0:
raise ValueError
except ValueError:
raise DatasetteError("_size must be a positive integer",
status=400)
if page_size > self.max_returned_rows:
raise DatasetteError("_size must be <= {}".format(
self.max_returned_rows),
status=400)
extra_args["page_size"] = page_size
else:
page_size = self.page_size
sql = "select {select} from {table_name} {where}{order_by}limit {limit}{offset}".format(
select=select,
table_name=escape_sqlite(table),
where=where_clause,
order_by=order_by,
limit=page_size + 1,
offset=offset,
)
if request.raw_args.get("_timelimit"):
extra_args["custom_time_limit"] = int(
request.raw_args["_timelimit"])
rows, truncated, description = await self.execute(name,
sql,
params,
truncate=True,
**extra_args)
# facets support
try:
facets = request.args["_facet"]
except KeyError:
facets = table_metadata.get("facets", [])
facet_results = {}
for column in facets:
facet_sql = """
select {col} as value, count(*) as count
{from_sql}
group by {col} order by count desc limit 20
""".format(col=escape_sqlite(column), from_sql=from_sql)
try:
facet_rows = await self.execute(name,
facet_sql,
params,
truncate=False,
custom_time_limit=200)
facet_results[column] = [{
"value":
row["value"],
"count":
row["count"],
"toggle_url":
urllib.parse.urljoin(
request.url,
path_with_added_args(request, {column: row["value"]}),
),
} for row in facet_rows]
except sqlite3.OperationalError:
# Hit time limit
pass
columns = [r[0] for r in description]
rows = list(rows)
filter_columns = columns[:]
if use_rowid and filter_columns[0] == "rowid":
filter_columns = filter_columns[1:]
# Pagination next link
next_value = None
next_url = None
if len(rows) > page_size and page_size > 0:
if is_view:
next_value = int(_next or 0) + page_size
else:
next_value = path_from_row_pks(rows[-2], pks, use_rowid)
# If there's a sort or sort_desc, add that value as a prefix
if (sort or sort_desc) and not is_view:
prefix = rows[-2][sort or sort_desc]
if prefix is None:
prefix = "$null"
else:
prefix = urllib.parse.quote_plus(str(prefix))
next_value = "{},{}".format(prefix, next_value)
added_args = {"_next": next_value}
if sort:
added_args["_sort"] = sort
else:
added_args["_sort_desc"] = sort_desc
else:
added_args = {"_next": next_value}
next_url = urllib.parse.urljoin(
request.url, path_with_added_args(request, added_args))
rows = rows[:page_size]
# Number of filtered rows in whole set:
filtered_table_rows_count = None
if count_sql:
try:
count_rows = list(await self.execute(name, count_sql, params))
filtered_table_rows_count = count_rows[0][0]
except sqlite3.OperationalError:
# Almost certainly hit the timeout
pass
# human_description_en combines filters AND search, if provided
human_description_en = filters.human_description_en(
extra=search_descriptions)
if sort or sort_desc:
sorted_by = "sorted by {}{}".format(
(sort or sort_desc), " descending" if sort_desc else "")
human_description_en = " ".join(
[b for b in [human_description_en, sorted_by] if b])
async def extra_template():
display_columns, display_rows = await self.display_columns_and_rows(
name,
table,
description,
rows,
link_column=not is_view,
expand_foreign_keys=True,
)
metadata = self.ds.metadata.get("databases",
{}).get(name,
{}).get("tables",
{}).get(table, {})
self.ds.update_with_inherited_metadata(metadata)
return {
"database_hash":
hash,
"supports_search":
bool(fts_table),
"search":
search or "",
"use_rowid":
use_rowid,
"filters":
filters,
"display_columns":
display_columns,
"filter_columns":
filter_columns,
"display_rows":
display_rows,
"is_sortable":
any(c["sortable"] for c in display_columns),
"path_with_added_args":
path_with_added_args,
"request":
request,
"sort":
sort,
"sort_desc":
sort_desc,
"disable_sort":
is_view,
"custom_rows_and_columns_templates": [
"_rows_and_columns-{}-{}.html".format(
to_css_class(name), to_css_class(table)),
"_rows_and_columns-table-{}-{}.html".format(
to_css_class(name), to_css_class(table)),
"_rows_and_columns.html",
],
"metadata":
metadata,
}
return {
"database": name,
"table": table,
"is_view": is_view,
"view_definition": view_definition,
"table_definition": table_definition,
"human_description_en": human_description_en,
"rows": rows[:page_size],
"truncated": truncated,
"table_rows_count": table_rows_count,
"filtered_table_rows_count": filtered_table_rows_count,
"columns": columns,
"primary_keys": pks,
"units": units,
"query": {
"sql": sql,
"params": params
},
"facet_results": facet_results,
"next": next_value and str(next_value) or None,
"next_url": next_url,
}, extra_template, (
"table-{}-{}.html".format(to_css_class(name), to_css_class(table)),
"table.html",
)
