change random value for quota test again

Release 0.8.2

Makefile

@@ -1,7 +1,7 @@
 # cartodb/Makefile
 
 EXTENSION = cartodb
-EXTVERSION = 0.7.2
+EXTVERSION = 0.8.2
 
 SED = sed
 
@@ -36,6 +36,11 @@ UPGRADABLE = \
   0.6.0 \
   0.7.0 \
   0.7.1 \
+  0.7.2 \
+  0.7.3 \
+  0.7.4 \
+  0.8.0 \
+  0.8.1 \
   $(EXTVERSION)dev \
   $(EXTVERSION)next \
   $(END)

NEWS.md

@@ -1,3 +1,30 @@
+0.8.2 (2015-07-27)
+------------------
+* Fix for CDB_UserTables returning wrong listings when publicuser is used
+
+0.8.1 (2015-06-30)
+------------------
+* Fix for [#95](https://github.com/CartoDB/cartodb-postgresql/issues/95) *cdb_usertables should return public tables when the user is publicuser*
+
+0.8.0 (2015-06-30)
+------------------
+* Adds new function CDB_QueryTablesText that can deal with "schema.table_name"
+  longer than 63 chars.
+* Adds a set of statistical functions:
+  - CDB_DistType
+  - CDB_DistinctMeasure
+  - CDB_EqualIntervalBins
+* Fix for CDB_UserTables returns 0 entries for multiuser accounts [#64](https://github.com/CartoDB/cartodb-postgresql/issues/64)
+
+0.7.4 (2015-06-29)
+------------------
+Dummy transitional version.
+
+0.7.3 (2015-03-03)
+------------------
+* Fix upgrade of CDB_StringToDate function
+* Add a test for to validate CDB_TableMetadataTouch usage with OID
+
 0.7.2 (2015-03-03)
 ------------------
 * Fix conversion of strings to datetime

README.md

@@ -11,7 +11,7 @@ See https://github.com/CartoDB/cartodb/wiki/CartoDB-PostgreSQL-extension
 Dependencies
 ------------
 
- * PostgreSQL 9.3+ (with plpythonu extension)
+ * PostgreSQL 9.3+ (with plpythonu extension and xml support)
  * [PostGIS extension](http://postgis.net) 
  * [Schema triggers extension]
    (https://bitbucket.org/malloclabs/pg_schema_triggers)

doc/CDB_ColumnNames.md

@@ -0,0 +1,14 @@
+Retrieve all column names in a particular table
+
+#### Using the function
+
+```sql
+SELECT CDB_ColumnNames('table_name')
+--- Returns a set of rows with column names
+```
+
+#### Arguments
+
+CDB_ColumnNames(table_name)
+
+* **table_name** text

doc/CDB_ColumnType.md

@@ -0,0 +1,15 @@
+Returns a column type for any column in a table
+
+#### Using the function
+
+```sql
+SELECT CDB_ColumnType('column_name','table_name')
+--- Returns a set of rows with column types
+```
+
+#### Arguments
+
+CDB_ColumnType(column_name, table_name)
+
+* **column_name** text
+* **table_name** text

doc/CDB_HeadsTailsBins.md

@@ -0,0 +1,21 @@
+Find the breaks for N categories in a numerical column based on the [Heads/Tails optimization](http://arxiv.org/pdf/1209.2801v1.pdf). Below, Heads/Tails used to color based on the area of the polygons.
+
+![headtails](https://f.cloud.github.com/assets/370259/140655/6eebb918-7228-11e2-89fa-149745f25d34.png)
+
+#### Using the function
+
+We can determine the 7 most optimal breaks in a column of numerical data as follows, 
+
+```sql
+SELECT CDB_HeadsTailsBins(array_agg(numeric_column), 7) FROM table_name
+-- Results in an ordered array like, {7824,23492,52696,233857,666089,1001709,1638094}
+-- Each break happens up to, and equal, to a number: 
+-- (bin1 is less than or equal to 7824, bin2 is less than or equal to 23492, etc.)
+```
+
+#### Arguments
+
+CDB_HeadsTailsBins(in_array, breaks)
+
+* **in_array** numeric[]. A NUMERIC array of values.
+* **breaks** int. The number of categories you want to create

doc/CDB_HexagonGrid.md

@@ -0,0 +1,43 @@
+Fill given extent with an hexagonal coverage
+
+#### Using the function
+
+Create a hexagonal grid from a polygon geometry. For example, take the geometry
+
+```sql
+  ST_SetSRID(
+    ST_Envelope(
+      ST_Collect(
+        ST_MakePoint(10000000,-10000000),
+        ST_MakePoint(-10000000,10000000)
+      )
+     ),
+     3857)
+```
+
+We can create a grid as follows, 
+
+```sql
+SELECT CDB_HexagonGrid(
+  ST_SetSRID(
+    ST_Envelope(
+      ST_Collect(
+        ST_MakePoint(10000000,-10000000),
+        ST_MakePoint(-10000000,10000000)
+      )
+     ),
+     3857),
+   1000000) the_geom_webmercator
+```
+
+Which will look something like this,
+
+![grid tile](http://i.imgur.com/4rZXGMb.png)
+
+#### Arguments
+
+CDB_HexagonGrid(ext, side, origin)
+
+* **ext** geometry. Extent to fill. Only hexagons with center point falling inside the extent (or at the lower or leftmost edge) will be emitted. The returned hexagons will have the same SRID as this extent.
+* **side** float. Side measure for the hexagon. Maximum diameter will be 2 * side. Measure is in the same projection as **ext**
+* **origin** OPTIONAL geometry. Optional origin to allow for exact tiling. If omitted the origin will be 0,0. The parameter is checked for having the same SRID as the extent.

doc/CDB_JenksBins.md

@@ -0,0 +1,23 @@
+Find the breaks for N categories in a numerical column based on the [Jenks optimization](http://en.wikipedia.org/wiki/Jenks_natural_breaks_optimization). Below, Jenks used to color based on the area of the polygons.
+
+![Jenks](https://f.cloud.github.com/assets/370259/140093/b64a9382-7210-11e2-81a4-c65cce3c885e.png)
+
+#### Using the function
+
+We can determine the 7 most optimal breaks in a column of numerical data as follows, 
+
+```sql
+SELECT CDB_JenksBins(array_agg(numeric_column), 7) FROM table_name
+-- Results in an ordered array like, {0,73,2568,9408,29411,768230,1638094}
+-- Each break happens up to, and equal, to a number: 
+-- (bin1 is less than or equal to 0, bin2 is less than or equal to 73, etc.)
+```
+
+#### Arguments
+
+CDB_JenksBins(in_array, breaks, invert)
+
+* **in_array** numeric[]. A NUMERIC array of values.
+* **breaks** int. The number of categories you want to create
+* **iterations** OPTIONAL int. The number of iterations used for calculating breaks.
+* **invert** OPTIONAL boolean. Flips whether you receive top down breaks or bottom up breaks. Default is top down (so, <=). Bottom up would give you values that define the lower-end start of a bin (so >=).

doc/CDB_MakeHexagon.md

@@ -0,0 +1,21 @@
+Return an Hexagon with given center and side (or maximal radius)
+
+#### Using the function
+
+Running the following SQL
+
+```sql
+SELECT CDB_MakeHexagon(ST_MakePoint(0,0),10000000)
+```
+
+Would give you back a single hexagon geometry, 
+
+![hexagon](http://i.imgur.com/6jeGStb.png)
+
+
+#### Arguments
+
+CDB_MakeHexagon(center, radius)
+
+* **center** geometry
+* **radius** float. Radius of hexagon measured in same projection as **center**

doc/CDB_QuantileBins.md

@@ -0,0 +1,21 @@
+Find the breaks for N categories in a numerical column based on the [Quantile bins]. Below, the quantile method is used to determine color based on the area of the polygons.
+
+![qunatile](https://f.cloud.github.com/assets/370259/140714/932ed0e6-722b-11e2-9807-ffbd0fddb9ac.png)
+
+#### Using the function
+
+We can determine the 7 most optimal breaks in a column of numerical data as follows, 
+
+```sql
+SELECT CDB_QuantileBins(array_agg(numeric_column), 7) FROM table_name
+-- Results in an ordered array like, {80,2281,7162,17652,39730,91077,1638094}
+-- Each break happens up to, and equal, to a number: 
+-- (bin1 is less than or equal to 80, bin2 is less than or equal to 2281, etc.)
+```
+
+#### Arguments
+
+CDB_QuantileBins(in_array, breaks)
+
+* **in_array** numeric[]. A NUMERIC array of values.
+* **breaks** int. The number of categories you want to create

doc/CDB_RectangleGrid.md

@@ -0,0 +1,46 @@
+Fill given extent with a rectangular coverage
+
+#### Using the function
+
+Create a rectangular grid from a polygon geometry. For example, take the geometry
+
+```sql
+  ST_SetSRID(
+    ST_Envelope(
+      ST_Collect(
+        ST_MakePoint(10000000,-10000000),
+        ST_MakePoint(-10000000,10000000)
+      )
+     ),
+     3857)
+```
+
+We can create a grid as follows, 
+
+```sql
+SELECT CDB_RectangleGrid(
+  ST_SetSRID(
+    ST_Envelope(
+      ST_Collect(
+        ST_MakePoint(10000000,-10000000),
+        ST_MakePoint(-10000000,10000000)
+      )
+     ),
+     3857),
+   1000000,
+   1000000
+) the_geom_webmercator
+```
+
+Which will look something like this,
+
+![rect grid](http://i.imgur.com/HuhOJRs.png)
+
+#### Arguments
+
+CDB_RectangleGrid(ext, width, height, origin)
+
+* **ext** geometry. Extent to fill. Only rectangles with center point falling inside the extent (or at the lower or leftmost edge) will be emitted. The returned hexagons will have the same SRID as this extent.
+* **width** float. Width of each rectangle. Measure is in the same projection as **ext**
+* **height** float. Height of each rectangle. Measure is in the same projection as **ext**
+* **origin** OPTIONAL geometry. Optional origin to allow for exact tiling. If omitted the origin will be 0,0. The parameter is checked for having the same SRID as the extent.

doc/CDB_SetUserQuotaInBytes.md

@@ -0,0 +1,11 @@
+Sets user quota in bytes (superuser only)
+
+#### Using the function
+
+```sql
+SELECT CDB_SetUserQuotaInBytes(10485760);
+--- Returns the previously set quota.
+--- Use 0 to disable quota.
+```
+
+REF: https://github.com/CartoDB/cartodb-postgresql/blob/master/scripts-available/CDB_Quota.sql

doc/CDB_TransformToWebmercator.md

@@ -0,0 +1,44 @@
+Function to "safely" transform to webmercator. This function is most useful for rendering custom geometries using the CartoDB tiler. Often, transforming a projection like WGS84 can cause issues with extents beyond what are actually valid in webmercator, this attempts to fix those issues.
+
+#### Using the function
+
+Using a box that is nearly the full globe,
+
+```sql
+ST_SetSRID(
+  ST_Envelope(
+    ST_Collect(
+      ST_MakePoint(-180,60),
+      ST_MakePoint(180,-60)
+    )
+   ),
+   4326
+)
+```
+
+We can then convert it to a renderable webmercator geometry.
+
+```sql
+SELECT CDB_TransformToWebmercator(
+ ST_SetSRID(
+  ST_Envelope(
+    ST_Collect(
+      ST_MakePoint(-10,60),
+      ST_MakePoint(300,-60)
+    )
+   ),
+   4326
+ )
+)
+```
+
+Would give you back a single valid rectangle in webmercator. Since a longitude of 300 would convert to an unallowed webmercator coordinate, it gets clipped first. Valid extent is WGS84 (-180, -89, 180, 89)
+
+![valid geom](http://i.imgur.com/EFdXiqt.png)
+
+
+#### Arguments
+
+CDB_TransformToWebmercator(geom)
+
+* **geom** geometry

doc/CDB_UserTables.md

@@ -0,0 +1,11 @@
+List the name of available tables (only the usable ones)
+
+#### Using the function
+
+```sql
+--- Returns a row for each table having given permission with the table name
+--- Currently accepted permissions are: 'public', 'private' or 'all'
+SELECT CDB_UserTables(perms)
+```
+
+REF: https://github.com/CartoDB/cartodb-postgresql/blob/master/scripts-available/CDB_UserTables.sql

doc/CDB_XYZ_Extent.md

@@ -0,0 +1,22 @@
+Determine the spatial extent of a tile based on the tile's XYZ coordinate.
+
+#### Using the function
+
+Take a common tile with coordinates x=3, y=2, z=2,
+
+![2/3/2](https://viz2.cartodb.com/tiles/quantile_breaks/2/3/2.png)
+
+To determine its extent you would run,
+
+```sql
+SELECT CDB_XYZ_Extent(3,2,2)
+--- Returns a WKB polygon in Webmercator (SRID 3857)
+```
+
+#### Arguments
+
+CDB_XYZ_Extent(x,y,z)
+
+* **x** integer
+* **y** integer
+* **z** integer

doc/CDB_XYZ_Resolution.md

@@ -0,0 +1,20 @@
+Return pixel resolution of tiles at a given zoom level
+
+#### Using the function
+
+Take a common tile with zoom, z=2,
+
+![2/3/2](https://viz2.cartodb.com/tiles/quantile_breaks/2/3/2.png)
+
+To determine the resolution of these pixels,
+
+```sql
+SELECT CDB_XYZ_Resolution(2)
+--- Returns a float, 39135.7587890625
+```
+
+#### Arguments
+
+CDB_XYZ_Resolution(z)
+
+* **z** integer

doc/CartoDB-PLpgSQL.md

@@ -0,0 +1,38 @@
+INTRODUCTION
+============
+
+CartoDB uses a number of custom [PLpgSQL](http://www.postgresql.org/docs/8.3/static/plpgsql.html) functions to perform a few magical things. Those functions are accessible to users on CartoDB as well, so we would like to document what they are and what they do here.
+
+## Spatial functions
+
+[CDB_HexagonGrid](CDB_HexagonGrid) - create hexagonal grid from extent and size
+
+[CDB_MakeHexagon](CDB_MakeHexagon) - make a hexagon with given center and side
+
+[CDB_RectangleGrid](CDB_RectangleGrid) - fill given extent with a rectangular coverage
+
+##### Tile based
+
+[CDB_XYZ_Extent](CDB_XYZ_Extent) - Find the extent of a tile by XYZ
+
+[CDB_XYZ_Resolution](CDB_XYZ_Resolution) - Find the pixel resolution of tiles
+
+[CDB_TransformToWebmercator](CDB_TransformToWebmercator) - Convert a geometry to valid webmercator
+
+## Statistical functions
+
+[CDB_JenksBins](CDB_JenksBins) - Find breaks in an array of numbers using Jenks method
+
+[CDB_HeadsTailsBins](CDB_HeadsTailsBins) - Find breaks in an array of numbers using Heads/Tails method
+
+[CDB_QuantileBins](CDB_QuantileBins) - Find quantile breaks in an array of numbers
+
+## System functions
+
+[CDB_UserTables](CDB_UserTables) - Get a list of all tables in your account
+
+[[CDB_SetUserQuotaInBytes]] - Set maximum user quota in bytes
+
+column names - now returned in JSON response
+
+column types - now returned in JSON response

doc/CartoDB-user-table.md

@@ -0,0 +1,29 @@
+A "cartodb" user table is a table with a well-known set of fields and a well-known set of triggers attached on. 
+
+The fields are:
+
+ - `cartodb_id`, a numerical primary key of serial type
+ - `created_at`, timestamp with timezone not null default now()
+ - `updated_at`, timestamp with timezone not null default now()
+ - `the_geom`, geometry, GiST indexed, constrained (see below)
+ - `the_geom_webmercator`, geometry, GiST indexed, constrained (see below)
+
+The values of "the_geom" and "the_geom_webmercator" must match these constraints:
+
+ - Only POINT, MULTILINE, MULTIPOLYGON types ? Maybe UNCONSTRAINED
+ - Only 2 dimensions ? Maybe UNCONSTRAINED
+ - SRID=4326 for the_geom and SRID=3857 for the_geom_webmercator
+
+The triggers are:
+
+ - `track_updates` after modifying statement updates cdb_tablemetadata
+ - `test_quota` before changing statement to forbid if overquota
+ - `test_quota_per_row` before changing row to forbod if overquota (checked on a probabilistic basis)
+ - `update_the_geom_webmercator` before insert or update row to maintain the_geom_webmercator
+ - `update_updated_at_trigger` before update row to maintain updated_at
+
+Some conversions will be attempted to perform upon cartodbfication when certain fields appear:
+
+ - `cartodb_id`: If found type TEXT will be attempted to cast
+ - `created_at`: If found type TEXT will be attempted to cast
+ - `updated_at`: If found type TEXT will be attempted to cast

doc/README.md

@@ -0,0 +1,48 @@
+# Contents
+
+* [CartoDB-user-table](CartoDB-user-table.md)
+* [CartoDB-PLpgSQL](CartoDB-PLpgSQL.md)
+* [CDB_ColumnNames](CDB_ColumnNames.md)
+* [CDB_ColumnType](CDB_ColumnType.md)
+* [CDB_HeadsTailsBins](CDB_HeadsTailsBins.md)
+* [CDB_HexagonGrid](CDB_HexagonGrid.md)
+* [CDB_JenksBins](CDB_JenksBins.md)
+* [CDB_MakeHexagon](CDB_MakeHexagon.md)
+* [CDB_QuantileBins](CDB_QuantileBins.md)
+* [CDB_RectangleGrid](CDB_RectangleGrid.md)
+* [CDB_SetUserQuotaInBytes](CDB_SetUserQuotaInBytes.md)
+* [CDB_TransformToWebmercator](CDB_TransformToWebmercator.md)
+* [CDB_UserTables](CDB_UserTables.md)
+* [CDB_XYZ_Extent](CDB_XYZ_Extent.md)
+* [CDB_XYZ_Resolution](CDB_XYZ_Resolution.md)
+
+The CartoDB PostgreSQL extension is a module to load into each CartoDB user database to perform cartodb-specific security and functionality checks.
+
+# Checks
+
+No user other than the superuser should be allowed to change `statement_timeout` for the session (SET statement_timeout disallowed).
+
+User tables need to match certain structure criteria (See [[CartoDB-user-table]]) so the extension should provide a mean to enforce such structure everytime an attempt to change structure is encountered. 
+
+# Events
+
+The events we want some function to be called upon are:
+
+| event                  | arguments to handler function        | function duty                    | OK* |
+|------------------------|--------------------------------------|----------------------------------|-----|
+| SET variable           | name of variable                     | forbid changing some vars        |     |
+| RENAME table           | old and new name + oid of the table  | flush cache                      |     |
+| ADD/DROP/ALTER column  | oid of the table                     | flush cache, cartodbfy, upd meta |  Y  |
+| DISABLE/DROP trigger   | oid of table, name of trigger        | cartodbfy or forbid              |     |
+| DROP table             | oid of the table                     | flush cache and metadata         |  Y  |
+| CREATE table           | oid of the table                     | cartodby, upd metadata           |  Y  |
+| GRANT                  | oid of table, privilege, role        | flush cache, upd metadata        |
+| REVOKE                 | oid of table, privilege, role        | flush cache, upd metadata        |
+
+
+* event available by installing https://github.com/CartoDB/pg_schema_triggers
+
+At this stage we don't need more than this, but the number of events and the number of arguments passed to the handler function may expand in the future, so the extension should be written in a way to easily allow that.
+
+Some of the handler will need to act _after_ the statement is completed (CREATE TABLE, for example).
+

scripts-available/CDB_DistType.sql

@@ -0,0 +1,122 @@
+--
+-- CDB_DistType classifies the histograms of a column into
+-- one of the basic types listed by Galtung: http://druedin.com/2012/12/08/galtungs-ajus-system/
+-- 
+-- Future improvements:
+--    variable number of bins (7 is baked in right now)
+--    catch the number of items to ensure that the sample is large enough
+--
+-- Refs:
+--    1. width_bucket/histograms: http://tapoueh.org/blog/2014/02/21-PostgreSQL-histogram
+--    2. R implementation: https://github.com/cran/agrmt
+
+CREATE OR REPLACE FUNCTION CDB_DistType ( in_array NUMERIC[] ) RETURNS text as $$
+DECLARE
+    element_count INT4;
+    minv numeric;
+    maxv numeric;
+    bins numeric[];
+    freqs numeric[];
+    ajus INT[];
+    freq INT4;
+    signature text;
+    i INT := 1;
+BEGIN
+    SELECT min(e), max(e), count(e) INTO minv, maxv, element_count FROM ( SELECT unnest(in_array) e ) x;
+
+    IF abs(maxv - minv) < 1e-7 THEN -- if max and min are nearly equal, call if 'F' (make relative to maxv?)
+        signature = 'F';
+    ELSE
+        -- Calculate bins and count in bins
+        EXECUTE 'WITH stats as (
+            SELECT min(e) as minv,
+                   max(e) as maxv,
+                   count(e) as total
+            FROM (SELECT unnest($1) e) x
+            WHERE e is not null
+        ),
+        hist as (
+            SELECT width_bucket(e, s.minv, s.maxv, 7) bucket,
+                   count(*) freq
+            FROM (SELECT unnest($1) e) x, stats s
+            WHERE e is not null
+            GROUP BY 1
+            ORDER BY 1
+        )
+        SELECT array_agg(round(100.0 * hist.freq::numeric / stats.total::numeric,1)) freqs,
+               array_agg(hist.bucket) buckets
+        FROM hist, stats'
+        INTO freqs, bins
+        USING in_array;
+
+        LOOP
+            IF i < 7 THEN
+                ajus[i] = CASE WHEN freqs[i] > freqs[i+1] THEN -1
+                               WHEN abs(freqs[i] - freqs[i+1]) <= 0.05 THEN 0
+                               ELSE 1 END;
+            ELSE
+                EXIT;
+            END IF;
+            i := i + 1;
+        END LOOP;
+
+        signature = _CDB_DistTypeClassify(ajus);
+    END IF;
+
+    RETURN signature;
+END;
+$$ language plpgsql IMMUTABLE;
+
+-- Classify data into AJUSFL
+
+CREATE OR REPLACE FUNCTION _CDB_DistTypeClassify ( in_array INT[] ) RETURNS text as $$
+DECLARE
+    element_count INT4;
+    maxv numeric;
+    minv numeric;
+    uniques INT[];
+    type text;
+BEGIN
+    SELECT max(e), min(e) INTO maxv, minv FROM ( SELECT unnest(in_array) e ) x;
+
+    IF (maxv = 0 AND minv = 0) THEN
+        type = 'F';
+    ELSIF maxv < 1 THEN
+        type = 'L';
+    ELSIF minv > -1 THEN
+        type = 'J';
+    ELSE
+        -- Get distinct elements ordered by original position
+        EXECUTE 'WITH b AS (
+            SELECT a
+            FROM (SELECT unnest($1) a) x
+        ),
+        c AS (
+            SELECT a, row_number() OVER () r
+            FROM b
+        ),
+        d AS (
+            SELECT DISTINCT a
+            FROM c
+        ),
+        e AS (
+            SELECT a FROM d ORDER BY (
+                SELECT r FROM c WHERE d.a = c.a ORDER BY r ASC LIMIT 1
+            ) ASC)
+        SELECT array_agg(a) FROM e'
+        INTO uniques
+        USING in_array;
+
+        -- Decide if it's an A, U, or other
+        IF (uniques = ARRAY[1,-1] OR uniques = ARRAY[1,0,-1] OR uniques = ARRAY[1,-1,0] OR uniques = ARRAY[0,1,-1]) THEN
+            type = 'A';
+        ELSIF (uniques = ARRAY[-1,1] OR uniques = ARRAY[-1,0,1] OR uniques = ARRAY[-1,1,0] OR uniques = ARRAY[0,-1,1]) THEN
+            type = 'U';
+        ELSE
+            type = 'S';
+        END IF;
+    END IF;
+
+    RETURN type;
+END;
+$$ language plpgsql IMMUTABLE;

scripts-available/CDB_DistinctMeasure.sql

@@ -0,0 +1,46 @@
+--
+-- CDB_DistinctMeasure 
+--     calculates the fraction of rows in the 10 most common distinct categories
+--     returns true if the number of rows in these 10 categories is >= 0.9 * total number of rows
+-- 
+-- 
+
+CREATE OR REPLACE FUNCTION CDB_DistinctMeasure ( in_array text[], threshold numeric DEFAULT null ) RETURNS numeric as $$
+DECLARE
+    element_count INT4;
+    maxval numeric;
+    passes numeric;
+BEGIN
+    SELECT count(e) INTO element_count FROM ( SELECT unnest(in_array) e ) x;
+
+    -- count number of occurrences per bin
+    -- calculate the normalized cumulative sum
+    -- return the max value: which corresponds nth entry 
+    -- for n <= 10 depending on # of distinct values
+    EXECUTE 'WITH a As (
+              SELECT
+                count(*) cnt
+              FROM
+                (SELECT * FROM unnest($2) e ) x
+              WHERE e is not null
+              GROUP BY e
+              ORDER BY cnt DESC
+            ),
+            b As (
+              SELECT
+                sum(cnt) OVER (ORDER BY cnt DESC) / $1 As cumsum
+              FROM a
+              LIMIT 10
+            )
+            SELECT max(cumsum) maxval FROM b'
+            INTO maxval
+            USING element_count, in_array;
+    IF threshold is null THEN
+        passes = maxval;
+    ELSE
+        passes = CASE WHEN (maxval >= threshold) THEN 1 ELSE 0 END;
+    END IF;
+
+    RETURN passes;
+END;
+$$ language plpgsql IMMUTABLE;

scripts-available/CDB_EqualIntervalBins.sql

@@ -0,0 +1,37 @@
+--
+-- Calculate the equal interval bins for a given column
+--
+-- @param in_array A numeric array of numbers to determine the best
+--                   to determine the bin boundary
+--
+-- @param breaks The number of bins you want to find.
+--  
+--
+-- Returns: upper edges of bins
+-- 
+--
+
+CREATE OR REPLACE FUNCTION CDB_EqualIntervalBins ( in_array NUMERIC[], breaks INT ) RETURNS NUMERIC[] as $$
+DECLARE 
+    diff numeric;
+    min_val numeric;
+    max_val numeric;
+    tmp_val numeric;
+    i INT := 1;
+    reply numeric[];
+BEGIN
+    SELECT min(e), max(e) INTO min_val, max_val FROM ( SELECT unnest(in_array) e ) x WHERE e IS NOT NULL;
+    diff = (max_val - min_val) / breaks::numeric;
+    LOOP
+        IF i < breaks THEN
+            tmp_val = min_val + i::numeric * diff;
+            reply = array_append(reply, tmp_val);
+            i := i+1;
+        ELSE
+            reply = array_append(reply, max_val);
+            EXIT;
+        END IF;
+    END LOOP;
+    RETURN reply;
+END;
+$$ language plpgsql IMMUTABLE;

scripts-available/CDB_QuantileBins.sql

@@ -15,18 +15,29 @@ DECLARE
     i INT := 1; 
     reply numeric[]; 
 BEGIN 
-    -- get our unique values
-    SELECT array_agg(e) INTO in_array FROM (SELECT unnest(in_array) e GROUP BY e ORDER BY e ASC) x;
-    -- get the total size of our row
-    element_count := array_upper(in_array, 1) - array_lower(in_array, 1); 
+    -- sort our values
+    SELECT array_agg(e) INTO in_array FROM (SELECT unnest(in_array) e ORDER BY e ASC) x;
+    -- get the total size of our data
+    element_count := array_length(in_array, 1); 
     break_size :=  element_count::numeric / breaks;
     -- slice our bread
     LOOP  
-        IF i > breaks THEN  EXIT;  END IF;  
-        SELECT e INTO tmp_val FROM ( SELECT unnest(in_array) e LIMIT 1 OFFSET round(break_size * i)) x;
+        IF i < breaks THEN
+            IF break_size * i % 1 > 0 THEN
+                SELECT e INTO tmp_val FROM ( SELECT unnest(in_array) e LIMIT 1 OFFSET ceil(break_size * i) - 1) x;
+            ELSE
+                SELECT avg(e) INTO tmp_val FROM ( SELECT unnest(in_array) e LIMIT 2 OFFSET ceil(break_size * i) - 1 ) x;
+            END IF;
+        ELSIF i = breaks THEN
+            -- select the last value
+            SELECT max(e) INTO tmp_val FROM ( SELECT unnest(in_array) e ) x;
+        ELSE
+            EXIT;
+        END IF;
+
         reply = array_append(reply, tmp_val);
-        i := i+1; 
-    END LOOP; 
-    RETURN reply; 
+        i := i+1;
+    END LOOP;
+    RETURN reply;
 END; 
-$$ language plpgsql IMMUTABLE;
+$$ language plpgsql IMMUTABLE;

scripts-available/CDB_QueryTables.sql

@@ -2,12 +2,12 @@
 --
 -- Requires PostgreSQL 9.x+
 --
-CREATE OR REPLACE FUNCTION CDB_QueryTables(query text)
-RETURNS name[]
+CREATE OR REPLACE FUNCTION CDB_QueryTablesText(query text)
+RETURNS text[]
 AS $$
 DECLARE
   exp XML;
-  tables NAME[];
+  tables text[];
   rec RECORD;
   rec2 RECORD;
 BEGIN
@@ -41,11 +41,11 @@ BEGIN
           xpath('//x:Relation-Name/text()', exp, ARRAY[ARRAY['x', 'http://www.postgresql.org/2009/explain']]) as x,
           xpath('//x:Relation-Name/../x:Schema/text()', exp, ARRAY[ARRAY['x', 'http://www.postgresql.org/2009/explain']]) as s
       )
-      SELECT unnest(x)::name as p, unnest(s)::name as sc from inp
+      SELECT unnest(x) as p, unnest(s) as sc from inp
     LOOP
       -- RAISE DEBUG 'tab: %', rec2.p;
       -- RAISE DEBUG 'sc: %', rec2.sc;
-      tables := array_append(tables, (rec2.sc || '.' || rec2.p)::name);
+      tables := array_append(tables, (rec2.sc || '.' || rec2.p));
     END LOOP;
 
     -- RAISE DEBUG 'Tables: %', tables;
@@ -65,3 +65,14 @@ BEGIN
   return tables;
 END
 $$ LANGUAGE 'plpgsql' VOLATILE STRICT;
+
+
+-- Keep CDB_QueryTables with same signature for backwards compatibility.
+-- It should probably be removed in the future.
+CREATE OR REPLACE FUNCTION CDB_QueryTables(query text)
+RETURNS name[]
+AS $$
+BEGIN
+  RETURN CDB_QueryTablesText(query)::name[];
+END
+$$ LANGUAGE 'plpgsql' VOLATILE STRICT;

scripts-available/CDB_StringToDate.sql

@@ -1,5 +1,6 @@
 -- Convert string to date
 --
+DROP FUNCTION IF EXISTS CDB_StringToDate(character varying);
 CREATE OR REPLACE FUNCTION CDB_StringToDate(input character varying)
 RETURNS TIMESTAMP AS $$
 DECLARE output TIMESTAMP;

scripts-available/CDB_UserTables.sql

@@ -5,35 +5,22 @@
 --
 -- Currently accepted permissions are: 'public', 'private' or 'all'
 --
+DROP FUNCTION IF EXISTS cdb_usertables(text);
 CREATE OR REPLACE FUNCTION CDB_UserTables(perm text DEFAULT 'all')
-RETURNS SETOF information_schema.sql_identifier
+RETURNS SETOF name
 AS $$
-  WITH usertables AS ( 
-    -- TODO: query CDB_TableMetadata for this ?
-    -- See http://github.com/CartoDB/cartodb/issues/254#issuecomment-26044777
-    SELECT table_name as t
-    FROM information_schema.tables
-    WHERE
-         table_type='BASE TABLE'
-     AND table_schema='public'
-     AND table_name NOT IN (
-      'cdb_tablemetadata',
-      'spatial_ref_sys'
-     )
-  ), perms AS (
-    SELECT t, has_table_privilege('public', 'public'||'.'||t, 'SELECT') as p
-    FROM usertables
-  )
-  SELECT t FROM perms
-  WHERE (
-    p = CASE WHEN $1 = 'private' THEN false
-                 WHEN $1 = 'public' THEN true
-                 ELSE not p -- none
-            END
-    OR $1 = 'all'
-  )
-  AND has_table_privilege('public'||'.'||t, 'SELECT')
-   ;
+
+SELECT c.relname 
+FROM pg_class c 
+JOIN pg_namespace n ON n.oid = c.relnamespace
+WHERE c.relkind = 'r' 
+AND c.relname NOT IN ('cdb_tablemetadata', 'spatial_ref_sys')
+AND n.nspname NOT IN ('pg_catalog', 'information_schema', 'topology')
+AND CASE WHEN perm = 'public' THEN has_table_privilege('publicuser', c.oid, 'SELECT')
+         WHEN perm = 'private' THEN has_table_privilege(current_user, c.oid, 'SELECT') AND NOT has_table_privilege('publicuser', c.oid, 'SELECT')
+         WHEN perm = 'all' THEN has_table_privilege(current_user, c.oid, 'SELECT') OR has_table_privilege('publicuser', c.oid, 'SELECT')
+         ELSE false END;
+
 $$ LANGUAGE 'sql';
 
 -- This is to migrate from pre-0.2.0 version

scripts-enabled/240-CDB_EqualIntervalBins.sql

@@ -0,0 +1 @@
+../scripts-available/CDB_EqualIntervalBins.sql

scripts-enabled/CDB_DistType.sql

@@ -0,0 +1 @@
+../scripts-available/CDB_DistType.sql

scripts-enabled/CDB_DistinctMeasure.sql

@@ -0,0 +1 @@
+../scripts-available/CDB_DistinctMeasure.sql

test/CDB_DistTypeTest.sql

@@ -0,0 +1,4 @@
+WITH data AS (
+    SELECT pow(x,3)::numeric x FROM generate_series(-100,100) x
+    ) 
+SELECT CDB_DistType(array_agg(x)) FROM data

test/CDB_DistTypeTest_expect

@@ -0,0 +1 @@
+A

test/CDB_DistinctMeasureTest.sql

@@ -0,0 +1,20 @@
+-- a - j add up to 89%, k-m add up to 11%
+WITH a As (
+	SELECT (
+		repeat('a',12) || 
+		repeat('b',11) || 
+		repeat('c',11) || 
+		repeat('d',10) || 
+		repeat('e',10) || 
+		repeat('f',9) || 
+		repeat('g',8) || 
+		repeat('h',7) || 
+		repeat('i',6) || 
+		repeat('j',5) || 
+		repeat('k',4) || 
+		repeat('l',4) || 
+		repeat('m',3)
+		)::text AS x 
+	) 
+
+SELECT CDB_DistinctMeasure(string_to_array(x,null),0.90) from a

test/CDB_DistinctMeasureTest_expect

@@ -0,0 +1 @@
+0

test/CDB_EqualIntervalBinsTest.sql

@@ -0,0 +1,5 @@
+WITH data AS (
+    SELECT array_agg(x::numeric) s FROM generate_series(1,300) x 
+        WHERE x % 5 != 0 AND x % 7 != 0
+    ) 
+SELECT round(unnest(CDB_EqualIntervalBins(s, 7)),7) FROM data

test/CDB_EqualIntervalBinsTest_expect

@@ -0,0 +1,7 @@
+43.5714286
+86.1428571
+128.7142857
+171.2857143
+213.8571429
+256.4285714
+299.0000000

test/CDB_QuantileBinsTest_expect

@@ -1,7 +1,7 @@
-16
+13
 29
 43
 57
 71
-83
+86
 99

test/CDB_QueryTablesTest.sql

@@ -31,6 +31,8 @@ create table sc.test (a int);
 insert into sc.test values (1);
 WITH inp AS ( select 'select * from sc.test'::text as q )
  SELECT q, CDB_QueryTables(q) from inp;
+DROP TABLE sc.test;
+DROP SCHEMA sc;
 
 WITH inp AS ( select 'SELECT
 * FROM geometry_columns'::text as q )

test/CDB_QueryTablesTest_expect

@@ -4,14 +4,20 @@ CREATE table "my'tab;le" as select 1|{}
 SELECT a.oid, b.oid FROM pg_class a, pg_class b|{pg_catalog.pg_class}
 SELECT 1 as col1; select 2 as col2|{}
 WARNING:  CDB_QueryTables cannot explain query: select 1 from nonexistant (42P01: relation "nonexistant" does not exist)
+CONTEXT:  PL/pgSQL function cdb_querytables(text) line 3 at RETURN
 ERROR:  relation "nonexistant" does not exist
+CONTEXT:  PL/pgSQL function cdb_querytables(text) line 3 at RETURN
 begin; select * from pg_class; commit;|{pg_catalog.pg_class}
 WARNING:  CDB_QueryTables cannot explain query: select * from test (42P01: relation "test" does not exist)
+CONTEXT:  PL/pgSQL function cdb_querytables(text) line 3 at RETURN
 ERROR:  relation "test" does not exist
+CONTEXT:  PL/pgSQL function cdb_querytables(text) line 3 at RETURN
 WITH a AS (select * from pg_class) select * from a|{pg_catalog.pg_class}
 CREATE SCHEMA
 CREATE TABLE
 INSERT 0 1
 select * from sc.test|{sc.test}
+DROP TABLE
+DROP SCHEMA
 SELECT
 * FROM geometry_columns|{pg_catalog.pg_attribute,pg_catalog.pg_class,pg_catalog.pg_namespace,pg_catalog.pg_type}

test/CDB_UserTablesTest.sql

@@ -1,11 +1,19 @@
-create table pub(a int);
-create table prv(a int);
-GRANT SELECT ON TABLE pub TO public;
-REVOKE SELECT ON TABLE prv FROM public;
+CREATE ROLE publicuser LOGIN;
+CREATE TABLE pub(a int);
+CREATE TABLE prv(a int);
+GRANT SELECT ON TABLE pub TO publicuser;
+REVOKE SELECT ON TABLE prv FROM publicuser;
 SELECT CDB_UserTables() ORDER BY 1;
 SELECT 'all',CDB_UserTables('all') ORDER BY 2;
 SELECT 'public',CDB_UserTables('public') ORDER BY 2;
 SELECT 'private',CDB_UserTables('private') ORDER BY 2;
 SELECT '--unsupported--',CDB_UserTables('--unsupported--') ORDER BY 2;
-drop table pub;
-drop table prv;
+-- now tests with public user
+\c contrib_regression publicuser
+SELECT 'all_publicuser',CDB_UserTables('all') ORDER BY 2;
+SELECT 'public_publicuser',CDB_UserTables('public') ORDER BY 2;
+SELECT 'private_publicuser',CDB_UserTables('private') ORDER BY 2;
+\c contrib_regression postgres
+DROP TABLE pub;
+DROP TABLE prv;
+DROP ROLE publicuser;

test/CDB_UserTablesTest_expect

@@ -1,3 +1,4 @@
+CREATE ROLE
 CREATE TABLE
 CREATE TABLE
 GRANT
@@ -8,5 +9,10 @@ all|prv
 all|pub
 public|pub
 private|prv
+You are now connected to database "contrib_regression" as user "publicuser".
+all_publicuser|pub
+public_publicuser|pub
+You are now connected to database "contrib_regression" as user "postgres".
 DROP TABLE
 DROP TABLE
+DROP ROLE

test/CDB_XYZ_ExtentTest.sql

@@ -5,5 +5,5 @@ inp AS ( select z0.z, r1.r as x, r2.r as y FROM zoom z0, range r1, range r2 WHER
 ext AS ( select x,y,z,CDB_XYZ_Extent(x,y,z) as g from inp )
 select X::text || ',' || Y::text || ',' || Z::text as xyz,
        st_xmin(g), st_xmax(g), st_ymin(g), st_ymax(g)
-       from ext;
+       from ext order by xyz;
 

test/CDB_XYZ_ExtentTest_expect

@@ -1,13 +1,13 @@
 0,0,0|-20037508.5|20037508.5|-20037508.5|20037508.5
 0,0,1|-20037508.5|0|0|20037508.5
-0,1,1|-20037508.5|0|-20037508.5|0
-1,0,1|0|20037508.5|0|20037508.5
-1,1,1|0|20037508.5|-20037508.5|0
 0,0,2|-20037508.5|-10018754.25|10018754.25|20037508.5
+0,1,1|-20037508.5|0|-20037508.5|0
 0,1,2|-20037508.5|-10018754.25|0|10018754.25
 0,2,2|-20037508.5|-10018754.25|-10018754.25|0
 0,3,2|-20037508.5|-10018754.25|-20037508.5|-10018754.25
+1,0,1|0|20037508.5|0|20037508.5
 1,0,2|-10018754.25|0|10018754.25|20037508.5
+1,1,1|0|20037508.5|-20037508.5|0
 1,1,2|-10018754.25|0|0|10018754.25
 1,2,2|-10018754.25|0|-10018754.25|0
 1,3,2|-10018754.25|0|-20037508.5|-10018754.25

test/extension/test.sh

@@ -302,6 +302,21 @@ function test_cdb_tablemetadatatouch() {
     sql "SELECT CDB_TableMetadataTouch('\"public\".touch_example');"
     sql "SELECT CDB_TableMetadataTouch('\"public\".\"touch_example\"');"
 
+    # Works with OID
+    sql postgres "SELECT tabname from CDB_TableMetadata;" should 'touch_example'
+    sql postgres "SELECT count(*) from CDB_TableMetadata;" should 1
+    TABLE_OID=`${CMD} -U postgres ${DATABASE} -c "SELECT attrelid FROM pg_attribute WHERE attrelid = 'touch_example'::regclass limit 1;" -A -t`
+
+    # quoted OID works
+    sql "SELECT CDB_TableMetadataTouch('${TABLE_OID}');"
+    sql postgres "SELECT tabname from CDB_TableMetadata;" should 'touch_example'
+    sql postgres "SELECT count(*) from CDB_TableMetadata;" should 1
+
+    # non quoted OID works
+    sql "SELECT CDB_TableMetadataTouch(${TABLE_OID});"
+    sql postgres "SELECT tabname from CDB_TableMetadata;" should 'touch_example'
+    sql postgres "SELECT count(*) from CDB_TableMetadata;" should 1
+
     #### test tear down
     sql 'DROP TABLE touch_example;'
 }

test/organization/test.sh

@@ -142,6 +142,8 @@ function setup() {
     log_info "############################# SETUP #############################"
     create_role_and_schema cdb_testmember_1
     create_role_and_schema cdb_testmember_2
+    sql "CREATE ROLE publicuser LOGIN;"
+    sql "GRANT CONNECT ON DATABASE \"${DATABASE}\" TO publicuser;"
 
     create_table cdb_testmember_1 foo
     sql cdb_testmember_1 'INSERT INTO cdb_testmember_1.foo VALUES (1), (2), (3), (4), (5);'
@@ -168,9 +170,11 @@ function tear_down() {
 
     sql "REVOKE CONNECT ON DATABASE \"${DATABASE}\" FROM cdb_testmember_1;"
     sql "REVOKE CONNECT ON DATABASE \"${DATABASE}\" FROM cdb_testmember_2;"
+    sql "REVOKE CONNECT ON DATABASE \"${DATABASE}\" FROM publicuser;"
 
     sql 'DROP ROLE cdb_testmember_1;'
     sql 'DROP ROLE cdb_testmember_2;'
+    sql 'DROP ROLE publicuser;'
 
     ${CMD} -c "DROP DATABASE ${DATABASE}"
 }
@@ -346,6 +350,25 @@ function test_cdb_querytables_does_not_return_functions_as_part_of_the_resultset
     sql postgres "select * from CDB_QueryTables('select * from cdb_testmember_1.foo, cdb_testmember_2.bar, plainto_tsquery(''foo'')');" should "{cdb_testmember_1.foo,cdb_testmember_2.bar}"
 }
 
+function test_cdb_usertables_should_work_with_orgusers() {
+    sql "GRANT USAGE ON SCHEMA cartodb TO publicuser;"
+    ${CMD} -d ${DATABASE} -f scripts-available/CDB_UserTables.sql
+    sql cdb_testmember_1 "CREATE TABLE test_perms_pub (a int)"
+    sql cdb_testmember_1 "CREATE TABLE test_perms_priv (a int)"
+    sql cdb_testmember_1 "GRANT SELECT ON TABLE test_perms_pub TO publicuser"
+    sql publicuser "SELECT count(*) FROM CDB_UserTables('all')" should 1
+    sql publicuser "SELECT count(*) FROM CDB_UserTables('public')" should 1
+    sql publicuser "SELECT count(*) FROM CDB_UserTables('private')" should 0
+    # the following tests are for https://github.com/CartoDB/cartodb-postgresql/issues/98
+    #sql cdb_testmember_2 "SELECT count(*) FROM CDB_UserTables('all')" should 1
+    #sql cdb_testmember_2 "SELECT count(*) FROM CDB_UserTables('public')" should 1
+    #sql cdb_testmember_2 "SELECT count(*) FROM CDB_UserTables('private')" should 0
+
+    sql cdb_testmember_1 "DROP TABLE test_perms_pub"
+    sql cdb_testmember_1 "DROP TABLE test_perms_priv"
+}
+
+
 #################################################### TESTS END HERE ####################################################