Simplified standard library

Close #426.

Signed-off-by: Nicolas Williams <nico@cryptonector.com>

builtin.c

@@ -693,19 +693,25 @@ static block bind_bytecoded_builtins(block b) {
 static const char* const jq_builtins[] = {
   "def map(f): [.[] | f];",
   "def select(f): if f then . else empty end;",
-  "def sort_by(f): _sort_by_impl(map([f]));",
+  "def sort(f): _sort_by_impl(map([f]));",
-  "def group_by(f): _group_by_impl(map([f]));",
+  "def sort_by(f): sort(f);",
-  "def unique: group_by(.) | map(.[0]);",
+  "def group(f): _group_by_impl(map([f]));",
-  "def unique_by(f): group_by(f) | map(.[0]);",
+  "def group_by(f): group(f);",
-  "def max_by(f): _max_by_impl(map([f]));",
+  "def unique: group(.) | map(.[0]);",
-  "def min_by(f): _min_by_impl(map([f]));",
+  "def unique(f): group(f) | map(.[0]);",
+  "def unique_by(f): unique(f);",
+  "def max(f): _max_by_impl(map([f]));",
+  "def min(f): _min_by_impl(map([f]));",
+  "def max_by(f): max(f);",
+  "def min_by(f): min(f);",
 #include "libm.h"
   "def add: reduce .[] as $x (null; . + $x);",
   "def del(f): delpaths([path(f)]);",
   "def _assign(paths; value): value as $v | reduce path(paths) as $p (.; setpath($p; $v));",
   "def _modify(paths; update): reduce path(paths) as $p (.; setpath($p; getpath($p) | update));",
   "def recurse(f): ., (f | select(. != null) | recurse(f));",
-  "def recurse_down: recurse(.[]?);",
+  "def recurse: recurse(.[]?);",
+  "def recurse_down: recurse;",
   "def to_entries: [keys[] as $k | {key: $k, value: .[$k]}];",
   "def from_entries: map({(.key): .value}) | add | .//={};",
   "def with_entries(f): to_entries | map(f) | from_entries;",
@@ -714,7 +720,7 @@ static const char* const jq_builtins[] = {
   "def index(i):   if type == \"array\" and (i|type) == \"array\" then .[i] elif type == \"array\" then .[[i]] else .[i] end | .[0];",
   "def rindex(i):  if type == \"array\" and (i|type) == \"array\" then .[i] elif type == \"array\" then .[[i]] else .[i] end | .[-1:][0];",
   "def paths: path(recurse(if (type|. == \"array\" or . == \"object\") then .[] else empty end))|select(length > 0);",
-  "def leaf_paths: . as $dot|paths|select(. as $p|$dot|getpath($p)|type|. != \"array\" and . != \"object\");",
+  "def paths(node_filter): . as $dot|paths|select(. as $p|$dot|getpath($p)|node_filter);",
   "def any: reduce .[] as $i (false; . or $i);",
   "def all: reduce .[] as $i (true; . and $i);",
   "def arrays: select(type == \"array\");",
@@ -726,9 +732,11 @@ static const char* const jq_builtins[] = {
   "def nulls: select(type == \"null\");",
   "def values: arrays, objects, booleans, numbers, strings;",
   "def scalars: select(. == null or . == true or . == false or type == \"number\" or type == \"string\");",
+  "def leaf_paths: paths(scalars);",
   "def join(x): reduce .[] as $i (\"\"; . + (if . == \"\" then $i else x + $i end));",
   "def flatten: reduce .[] as $i ([]; if $i | type == \"array\" then . + ($i | flatten) else . + [$i] end);",
   "def flatten(x): reduce .[] as $i ([]; if $i | type == \"array\" and x > 0 then . + ($i | flatten(x-1)) else . + [$i] end);",
+  "def range(x): range(0;x);",
 };
 #undef LIBM_DD
 

docs/content/3.manual/manual.yml

@@ -708,29 +708,25 @@ sections:
             input: '[1,2,3]'
             output: ['[2,3,4]']
 
-      - title: "`paths`"
+      - title: "`paths`, `paths(node_filter)`, `leaf_paths`"
         body: |
 
-          Outputs the paths to all the elements in its input (except it
+          `paths` outputs the paths to all the elements in its input
-          does not output the empty list, representing . itself).
+          (except it does not output the empty list, representing .
+          itself).
           
-          `paths` is equivalent to 
+          `paths(f)` outputs the paths to any values for which `f` is true.
+          That is, `paths(numbers)` outputs the paths to all numeric
+          values.
 
-              def paths: path(recurse(if (type|. == "array" or . == "object") then .[] else empty end))|select(length > 0);
+          `leaf_paths` is an alias of `paths(scalars)`; `leaf_paths` is
+          *deprecated* and will be removed in the next major release.
           
         examples:
           - program: '[paths]'
             input: '[1,[[],{"a":2}]]'
             output: ['[[0],[1],[1,0],[1,1],[1,1,"a"]]']
-
+          - program: '[paths(scalars)]'
-      - title: "`leaf_paths`"
-        body: |
-
-          Outputs the paths to all the leaves (non-array, non-object
-          elements) in its input.
-
-        examples:
-          - program: '[leaf_paths]'
             input: '[1,[[],{"a":2}]]'
             output: ['[[0],[1,1,"a"]]']
 
@@ -818,7 +814,7 @@ sections:
             input: '[{"foo": "bar"}, [{"foo": "baz"}]]'
             output: ['[{"foo": "bar"}, {"foo": "baz"}]']
 
-      - title: "`range`"
+      - title: "`range(upto), `range(from;upto)`"
         body: |
           
           The `range` function produces a range of numbers. `range(4;10)`
@@ -826,6 +822,8 @@ sections:
           are produced as separate outputs. Use `[range(4;10)]` to get a range as 
           an array.
           
+          Its first argument can be omitted; it defaults to zero.
+
         examples:
           - program: 'range(2;4)'
             input: 'null'
@@ -833,6 +831,9 @@ sections:
           - program: '[range(2;4)]'
             input: 'null'
             output: ['[2,3]']
+          - program: '[range(4)]'
+            input: 'null'
+            output: ['[0,1,2,3]']
             
       - title: "`floor`"
         body: |
@@ -890,7 +891,7 @@ sections:
             input: '[0, false, [], {}, null, "hello"]'
             output: ['["number", "boolean", "array", "object", "null", "string"]']
 
-      - title: "`sort, sort_by`"
+      - title: "`sort, sort(path_expression), sort_by(path_expression)`"
         body: |
           
           The `sort` functions sorts its input, which must be an
@@ -909,23 +910,27 @@ sections:
           sorted order), and if their keys are equal then the values
           are compared key by key.
 
-          `sort_by` may be used to sort by a particular field of an
+          `sort` may be used to sort by a particular field of an
-          object, or by applying any jq filter. `sort_by(foo)`
+          object, or by applying any jq filter.
-          compares two elements by comparing the result of `foo` on
+
-          each element.
+          `sort(foo)` compares two elements by comparing the result of
+          `foo` on each element.
+          
+          `sort_by(foo)` is an alias of `sort(foo)`; `sort_by()` is
+          *deprecated* and will be removed in the next major release.
 
         examples:
           - program: 'sort'
             input: '[8,3,null,6]'
             output: ['[null,3,6,8]']
-          - program: 'sort_by(.foo)'
+          - program: 'sort(.foo)'
             input: '[{"foo":4, "bar":10}, {"foo":3, "bar":100}, {"foo":2, "bar":1}]'
             output: ['[{"foo":2, "bar":1}, {"foo":3, "bar":100}, {"foo":4, "bar":10}]']
 
-      - title: "`group_by`"
+      - title: "`group(path_expression)`, `group_by(path_expression)`"
         body: |
           
-          `group_by(.foo)` takes as input an array, groups the
+          `group(.foo)` takes as input an array, groups the
           elements having the same `.foo` field into separate arrays,
           and produces all of these arrays as elements of a larger
           array, sorted by the value of the `.foo` field.
@@ -934,57 +939,61 @@ sections:
           place of `.foo`. The sorting order is the same as described
           in the `sort` function above.
           
+          `group_by(foo)` is an alias of `group(foo)`; `group_by()` is
+          *deprecated* and will be removed in the next major release.
+          
         examples:
-          - program: 'group_by(.foo)'
+          - program: 'group(.foo)'
             input: '[{"foo":1, "bar":10}, {"foo":3, "bar":100}, {"foo":1, "bar":1}]'
             output: ['[[{"foo":1, "bar":10}, {"foo":1, "bar":1}], [{"foo":3, "bar":100}]]']
 
-      - title: "`min`, `max`, `min_by`, `max_by`"
+      - title: "`min`, `max`, `min(path_exp)`, `max(path_exp)`, `min_by(path_exp)`, `max_by(path_exp)`"
         body: |
           
-          Find the minimum or maximum element of the input array. The
+          Find the minimum or maximum element of the input array.
-          `_by` versions allow you to specify a particular field or
+          This filter accepts an optional argument that
-          property to examine, e.g. `min_by(.foo)` finds the object
+          allows you to specify a particular field or
+          property to examine, e.g. `min(.foo)` finds the object
           with the smallest `foo` field.
           
+          For legacy reasons, `min_by(.foo)` and `max_by(.foo)` exist as
+          aliases for `min(.foo)` and `max(.foo)`. These aliases are
+          considered *deprecated* and will be removed in the next major
+          release.
+
         examples:
           - program: 'min'
             input: '[5,4,2,7]'
             output: ['2']
-          - program: 'max_by(.foo)'
+          - program: 'max(.foo)'
             input: '[{"foo":1, "bar":14}, {"foo":2, "bar":3}]'
             output: ['{"foo":2, "bar":3}']
 
-      - title: "`unique`"
+      - title: "`unique`, `unique(path_exp)`, `unique_by(path_exp)`"
         body: |
           
           The `unique` function takes as input an array and produces
           an array of the same elements, in sorted order, with
-          duplicates removed.
+          duplicates removed. If an optional argument is passed, it
+          will keep only one element for each value obtained by applying
+          the argument. Think of it as making an array by taking one
+          element out of every group produced by `group`.
+          
+          For legacy reasons, `unique_by(.foo)` exists as an alias for
+          `unique(.foo)`. This alias is considered *deprecated* and will
+          be removed in the next major release.
 
         examples:
           - program: 'unique'
             input: '[1,2,5,3,5,3,1,3]'
             output: ['[1,2,3,5]']
-
+          - program: 'unique(.foo)'
-      - title: "`unique_by`"
-        body: |
-          
-          The `unique_by(.foo)` function takes as input an array and produces
-          an array of the same elements, in sorted order, with
-          elqements with a duplicate `.foo` field removed. Think of it as making
-          an array by taking one element out of every group produced by
-          `group_by`.
-        
-        examples:
-          - program: 'unique_by(.foo)'
             input: '[{"foo": 1, "bar": 2}, {"foo": 1, "bar": 3}, {"foo": 4, "bar": 5}]'
             output: ['[{"foo": 1, "bar": 2}, {"foo": 4, "bar": 5}]']
-          - program: 'unique_by(length)'
+          - program: 'unique(length)'
             input: '["chunky", "bacon", "kitten", "cicada", "asparagus"]'
             output: ['["chunky", "bacon", "asparagus"]']
 
-
       - title: "`reverse`"
         body: |
           
@@ -1144,10 +1153,10 @@ sections:
             output: ['"a, b,c,d, e"']
 
 
-      - title: "`recurse`"
+      - title: "`recurse(f)`, `recurse`, `recurse_down`"
         body: |
           
-          The `recurse` function allows you to search through a
+          The `recurse(f)` function allows you to search through a
           recursive structure, and extract interesting data from all
           levels. Suppose your input represents a filesystem:
 
@@ -1166,6 +1175,13 @@ sections:
 
               recurse(.children[]) | .name
           
+          When called without an argument, `recurse` is equivalent to
+          `recurse(.[]?)`.
+          
+          For legacy reasons, `recurse_down` exists as an alias to
+          calling `recurse` without arguments. This alias is considered
+          *deprecated* and will be removed in the next major release.
+
         examples:
           - program: 'recurse(.foo[])'
             input: '{"foo":[{"foo": []}, {"foo":[{"foo":[]}]}]}'
@@ -1174,20 +1190,21 @@ sections:
               - '{"foo":[]}'
               - '{"foo":[{"foo":[]}]}'
               - '{"foo":[]}'
-
+          - program: 'recurse'
-      - title: "`recurse_down`"
+            input: '{"a":0,"b":[1]}'
-        body: |
+            output: 
-          
+              - '0'
-          A quieter version of `recurse(.[])`, equivalent to:
+              - '[1]'
-
+              - '1'
-              def recurse_down: recurse(.[]?);
 
       - title: "`..`"
         body: |
           
-          Short-hand for `recurse_down`.  This is intended to resemble
+          Short-hand for `recurse` without arguments.  This is intended
-          the XPath `//` operator.  Note that `..a` does not work; use
+          to resemble the XPath `//` operator.  Note that `..a` does not
-          `..|a` instead.
+          work; use `..|a` instead.  In the example below we use
+          `..|.a?` to find all the values of object keys "a" in any
+          object found "below" `.`.
 
         examples:
           - program: '..|.a?'

parser.y

@@ -477,7 +477,7 @@ Term:
   $$ = gen_noop(); 
 } |
 REC {
-  $$ = gen_call("recurse_down", gen_noop());
+  $$ = gen_call("recurse", gen_noop());
 } |
 Term FIELD '?' {
   $$ = gen_index_opt($1, gen_const($2));