Update nested structure of maps and vectors - clojure

I have a map with a vector of map like this:
{:tags ["type:something" "gw:somethingelse"],
:sources [{:tags ["s:my:tags"],
:metrics [{:tags ["a tag"]}
{:tags ["a noether tag" "aegn"]}
{:tags ["eare" "rh"]}]}]}
Note that there can be multiple sources, and multiple metrics.
Now I want to update the :metrics with an id by looking at the value of the tags.
Example: if ["a tag"] matches with for example id 1, and ["a noether tag" "aegn"] with id 2 I want the updated structure to look like this:
{:tags ["type:something" "gw:somethingelse"],
:sources [{:tags ["s:my:tags"],
:metrics [{:tags ["a tag"]
:id 1}
{:tags ["a noether tag" "aegn"]
:id 2}
{:tags ["eare" "rh"]}]}]}
I made a function transform that can convert a tag to an id. E.g, (transform "a tag") returns 1.
Now, when I try do add the ids with a for-comprehension I miss the old structure (only the inner ones get returned) and with assoc-in I have to know the indices upfront.
How can I perform this transformation elegantly?

i would start bottom up, making transformation function for :tags entry, then for :metrics and then for :sources.
let's say our transform function produces ids just by counting tags (just for illustration, it could be easily changed later):
(defn transform [tags] (count tags))
user> (transform ["asd" "dsf"])
;;=> 2
then apply transformation the metric entry:
(defn transform-metric [{:keys [tags] :as m}]
(assoc m :id (transform tags)))
user> (transform-metric {:tags ["a noether tag" "aegn"]})
;;=> {:tags ["a noether tag" "aegn"], :id 2}
now use transform-metric to update source entry:
(defn transform-source [s]
(update s :metrics #(mapv transform-metric %)))
user> (transform-source {:tags ["s:my:tags"],
:metrics [{:tags ["a tag"]}
{:tags ["a noether tag" "aegn"]}
{:tags ["eare" "rh"]}]})
;;=> {:tags ["s:my:tags"],
;; :metrics [{:tags ["a tag"], :id 1}
;; {:tags ["a noether tag" "aegn"], :id 2}
;; {:tags ["eare" "rh"], :id 2}]}
and the last step is to transform the whole data:
(defn transform-data [d]
(update d :sources #(mapv transform-source %)))
user> (transform-data data)
;;=> {:tags ["type:something" "gw:somethingelse"],
;; :sources [{:tags ["s:my:tags"],
;; :metrics [{:tags ["a tag"], :id 1}
;; {:tags ["a noether tag" "aegn"], :id 2}
;; {:tags ["eare" "rh"], :id 2}]}]}
so, we're done here.
Now notice that transform-data and transform-source are almost identical, so we can make an utility function that generates such updating functions:
(defn make-vec-updater [field transformer]
(fn [data] (update data field (partial mapv transformer))))
with this function we can define deep transformations like this:
(def transformer
(make-vec-updater
:sources
(make-vec-updater
:metrics
(fn [{:keys [tags] :as m}]
(assoc m :id (transform tags))))))
user> (transformer data)
;;=> {:tags ["type:something" "gw:somethingelse"],
;; :sources [{:tags ["s:my:tags"],
;; :metrics [{:tags ["a tag"], :id 1}
;; {:tags ["a noether tag" "aegn"], :id 2}
;; {:tags ["eare" "rh"], :id 2}]}]}
and based on this transformer construction approach we can make a nice function to update the values in vectors-of-maps-of-vectors-of-maps-of-vectors... structures, with arbitrary nesting level:
(defn update-in-v [data ks f]
((reduce #(make-vec-updater %2 %1) f (reverse ks)) data))
user> (update-in-v data [:sources :metrics]
(fn [{:keys [tags] :as m}]
(assoc m :id (transform tags))))
;;=> {:tags ["type:something" "gw:somethingelse"],
;; :sources [{:tags ["s:my:tags"],
;; :metrics [{:tags ["a tag"], :id 1}
;; {:tags ["a noether tag" "aegn"], :id 2}
;; {:tags ["eare" "rh"], :id 2}]}]}
UPDATE
in addition to this manual approach, there is a fantastic lib called specter out there, that does exactly the same thing (and much more), but is obviously more universal and usable:
(require '[com.rpl.specter :as sp])
(sp/transform [:sources sp/ALL :metrics sp/ALL]
(fn [{:keys [tags] :as m}]
(assoc m :id (transform tags)))
data)
;;=> {:tags ["type:something" "gw:somethingelse"],
;; :sources [{:tags ["s:my:tags"],
;; :metrics [{:tags ["a tag"], :id 1}
;; {:tags ["a noether tag" "aegn"], :id 2}
;; {:tags ["eare" "rh"], :id 2}]}]}

(use 'clojure.walk)
(def transform {["a tag"] 1
["a noether tag" "aegn"] 2})
(postwalk #(if-let [id (transform (:tags %))]
(assoc % :id id)
%)
data)
Output:
{:tags ["type:something" "gw:somethingelse"],
:sources
[{:tags ["s:my:tags"],
:metrics
[{:tags ["a tag"], :id 1}
{:tags ["a noether tag" "aegn"], :id 2}
{:tags ["eare" "rh"]}]}]}

Related

Spec: partially overriding generators in a map spec

Assuming I have already defined a spec from which I'd like to generate test data:
(s/def :customer/id uuid?)
(s/def :customer/given-name string?)
(s/def :customer/surname string?)
(s/def :customer/age pos?)
(s/def ::customer
(s/keys
:req-un [:customer/id
:customer/given-name
:customer/surname
:customer/age]))
In generating test data, I'd like to override how ids are generated in order to ensure they're from a smaller pool to encourage collisions:
(defn customer-generator
[id-count]
(gen/let [id-pool (gen/not-empty (gen/vector (s/gen :customer/id) id-count))]
(assoc (s/gen ::customer) :id (gen/element id-pool))))
Is there a way I can simplify this by overriding the :customer/id generator in my test code and then just using (s/gen ::customer)? So, something like the following:
(with-generators [:customer/id (gen/not-empty (gen/vector (s/gen :customer/id) id-count)))]
(s/gen ::customer))
Officially, you can override generators for specs by passing an overrides map to s/gen (See the docstring for more details):
(s/def :customer/id uuid?)
(s/def :customer/given-name string?)
(s/def :customer/surname string?)
(s/def :customer/age nat-int?)
(s/def ::customer
(s/keys
:req-un [:customer/id
:customer/given-name
:customer/surname
:customer/age]))
(def fixed-customer-id (java.util.UUID/randomUUID))
fixed-customer-id
;=> #uuid "c73ff5ea-8702-4066-a31d-bc4cc7015811"
(gen/generate (s/gen ::customer {:customer/id #(s/gen #{fixed-customer-id})}))
;=> {:id #uuid "c73ff5ea-8702-4066-a31d-bc4cc7015811",
; :given-name "1042IKQhd",
; :surname "Uw0AzJzj",
; :age 104}
Alternatively, there is a library for such stuff named genman, which I developed before :)
Using it, you can also write as:
(require '[genman.core :as genman :refer [defgenerator]])
(def fixed-customer-id (java.util.UUID/randomUUID))
(genman/with-gen-group :test
(defgenerator :customer/id
(s/gen #{fixed-customer-id})))
(genman/with-gen-group :test
(gen/generate (genman/gen ::customer)))
Clojure spec uses test.check internally to generate sample values. Here is how test.check can be overridden. Whenever trying to write unit tests with a "fake" function, with-redefs is your friend:
(ns tst.demo.core
(:use tupelo.core tupelo.test)
(:require
[clojure.test.check.generators :as gen]
))
(def id-gen gen/uuid)
(dotest
(newline)
(spyx-pretty (take 3 (gen/sample-seq id-gen)))
(newline)
(with-redefs [id-gen (gen/choose 1 5)]
(spyx-pretty (take 33 (gen/sample-seq id-gen))))
(newline)
)
with result:
-----------------------------------
Clojure 1.10.3 Java 15.0.2
-----------------------------------
Testing tst.demo.core
(take 3 (gen/sample-seq id-gen)) =>
[#uuid "cbfea340-1346-429f-ba68-181e657acba5"
#uuid "7c119cf7-0842-4dd0-a23d-f95b6a68f808"
#uuid "ca35cb86-1385-46ad-8fc2-e05cf7a1220a"]
(take 33 (gen/sample-seq id-gen)) =>
[5 4 3 3 2 2 3 1 2 1 4 1 2 2 4 3 5 2 3 5 3 2 3 2 3 5 5 5 5 1 3 2 2]
Example created
using my favorite template project.
Update
Unfortunately, the above technique does not work for Clojure Spec since (s/def ...) uses a global registery of Spec definitions, and is therefore immune to with-redefs. However, we can overcome this definition by simply redefining the desired spec in the unit test namespace like:
(ns tst.demo.core
(:use tupelo.core tupelo.test)
(:require
[clojure.spec.alpha :as s]
[clojure.spec.gen.alpha :as gen]
))
(s/def :app/id (s/int-in 9 99))
(s/def :app/name string?)
(s/def :app/cust (s/keys :req-un [:app/id :app/name]))
(dotest
(newline)
(spyx-pretty (gen/sample (s/gen :app/cust)))
(newline)
(s/def :app/id (s/int-in 2 5)) ; overwrite the definition of :app/id for testing
(spyx-pretty (gen/sample (s/gen :app/cust)))
(newline))
with result
-----------------------------------
Clojure 1.10.3 Java 15.0.2
-----------------------------------
Testing tst.demo.core
(gen/sample (s/gen :app/cust)) =>
[{:id 10, :name ""}
{:id 9, :name "n"}
{:id 10, :name "fh"}
{:id 9, :name "aI"}
{:id 11, :name "8v5F"}
{:id 10, :name ""}
{:id 10, :name "7"}
{:id 10, :name "3m6Wi"}
{:id 13, :name "OG2Qzfqe"}
{:id 10, :name ""}]
(gen/sample (s/gen :app/cust)) =>
[{:id 3, :name ""}
{:id 3, :name ""}
{:id 2, :name "5e"}
{:id 3, :name ""}
{:id 2, :name "y01C"}
{:id 3, :name "l2"}
{:id 3, :name "c"}
{:id 3, :name "pF"}
{:id 4, :name "0yrxyJ7l"}
{:id 4, :name "40"}]
So, it's a little ugly, but the redefinition of :app/id does the trick, and it only takes effect during unit test runs, leaving the main application unaffected.
user> (def ^:dynamic *idgen* (s/gen uuid?))
#'user/*idgen*
user> (s/def :customer/id (s/with-gen uuid? (fn [] ##'*idgen*)))
:customer/id
user> (s/def :customer/age pos-int?)
:customer/age
user> (s/def ::customer (s/keys :req-un [:customer/id :customer/age]))
:user/customer
user> (gen/sample (s/gen ::customer))
({:id #uuid "d18896f1-6199-42bf-9be3-3d0652583902", :age 1}
{:id #uuid "b6209798-4ffa-4e20-9a76-b3a799a31ec6", :age 2}
{:id #uuid "6f9c6400-8d79-417c-bc62-6b4557f7d162", :age 1}
{:id #uuid "47b71396-1b5f-4cf4-bd80-edf4792300c8", :age 2}
{:id #uuid "808692b9-0698-4fb8-a0c5-3918e42e8f37", :age 2}
{:id #uuid "ba663f0a-7c99-4967-a2df-3ec6cb04f514", :age 1}
{:id #uuid "8521b611-c38c-4ea9-ae84-35c8a2d2ff2f", :age 4}
{:id #uuid "c559d48d-4c50-438f-846c-780cdcdf39d5", :age 3}
{:id #uuid "03c2c114-03a0-4709-b9dc-6d326a17b69d", :age 40}
{:id #uuid "14715a50-81c5-48e4-bffe-e194631bb64b", :age 4})
user> (binding [*idgen* (let [idpool (gen/sample (s/gen :customer/id) 5)] (gen/elements idpool))] (gen/sample (s/gen ::customer)))
({:id #uuid "3e64131d-e7ad-4450-993d-fa651339df1c", :age 2}
{:id #uuid "575b2bef-956d-4c42-bdfa-982c7756a33c", :age 1}
{:id #uuid "575b2bef-956d-4c42-bdfa-982c7756a33c", :age 1}
{:id #uuid "3e64131d-e7ad-4450-993d-fa651339df1c", :age 1}
{:id #uuid "1a2eafed-8242-4229-b432-99edb361569d", :age 3}
{:id #uuid "1a2eafed-8242-4229-b432-99edb361569d", :age 1}
{:id #uuid "05bd521a-26f9-46e0-8b26-f798e0bf0452", :age 3}
{:id #uuid "575b2bef-956d-4c42-bdfa-982c7756a33c", :age 19}
{:id #uuid "31b80714-7ae0-40a0-b932-f7b5f078f2ad", :age 2}
{:id #uuid "05bd521a-26f9-46e0-8b26-f798e0bf0452", :age 5})
user>
A little clumsier than what you wanted, but maybe this is adequate.
You are probably better off using binding rather than with-redefs since binding modifies thread-local bindings, whereas with-redefs changes the root binding.
Since this is for generating bad test data, I'd consider avoiding the use of dynamic vars and binding altogether and just use a different spec that is only local to the test env.

Clojure: Is there a way to remove a key but keep its values

I need some help with a pickle. I have the below map
(def my-list
{:data-0
{:a1 ;;this is the value for :ward-room
{:type "Specialist"
:name "Dr Spongebob"
:illness "dehydration"
:ward-room "a1"}}
:data-1
{:b5
{:type "GP"
:name "Dr Patrick"
:illness "fishy eyes"}
:ward-room "b5"}})
I want to transform this into a map such as below
(def my-new-list
{:data-0
{:type "Specialist"
:name "Dr Spongebob"
:illness "dehydration"
:ward-room "a1"}
:data-1
{:type "GP"
:name "Dr Patrick"
:illness "fishy eyes"}
:ward-room "b5"}})
I couldn't figure out how to do this so I've tried using seq and then flatten but have not had success. Im not too sure how to get started Solving this problem. I would really appreciate a little help
considering corrected structure, with :ward-room having the same nesting level for both entries:
(def my-list
{:data-0
{:a1 ;;this is the value for :ward-room
{:type "Specialist"
:name "Dr Spongebob"
:illness "dehydration"
:ward-room "a1"}}
:data-1
{:b5
{:type "GP"
:name "Dr Patrick"
:illness "fishy eyes"
:ward-room "b5"}}})
there are some options:
first of all you could use reduce-kv, remapping to new vals:
(reduce-kv
(fn [acc k v] (assoc acc k (val (first v))))
{}
my-list)
;; {:data-0
;; {:type "Specialist",
;; :name "Dr Spongebob",
;; :illness "dehydration",
;; :ward-room "a1"},
;; :data-1
;; {:type "GP",
;; :name "Dr Patrick",
;; :illness "fishy eyes",
;; :ward-room "b5"}}
or you could use zipmap to zip keys with new vals:
(zipmap (keys my-list)
(map (comp val first val) my-list))
also there is a nice way to do it with functional composition:
(into {} (map (juxt key (comp val first val))) my-list)
Another approach is to splice the entries for every internal map at the upper level. This would also work for 'malformed' data, like yours:
(def my-list
{:data-0
{:a1 ;;this is the value for :ward-room
{:type "Specialist"
:name "Dr Spongebob"
:illness "dehydration"
:ward-room "a1"}}
:data-1
{:b5
{:type "GP"
:name "Dr Patrick"
:illness "fishy eyes"}
:ward-room "b5"}})
(defn lift-entries [old-entries]
(into {} (mapcat #(if (map? (val %))
(val %)
[%]))
old-entries))
(zipmap (keys my-list) (map lift-entries (vals my-list)))
;; {:data-0
;; {:type "Specialist",
;; :name "Dr Spongebob",
;; :illness "dehydration",
;; :ward-room "a1"},
;; :data-1
;; {:type "GP",
;; :name "Dr Patrick",
;; :illness "fishy eyes",
;; :ward-room "b5"}}
I think your data sample had a cut/paste error. Here is a simple answer:
(def my-data
{:data-0 {:a1 {:type "Specialist"
:name "Dr Spongebob"
:illness "dehydration"
:ward-room "a1"}}
:data-1 {:b5 {:type "GP"
:name "Dr Patrick"
:illness "fishy eyes"
:ward-room "b5"
}}})
(defn delete-intermediate-level
[data]
(into {}
(for [[k1 v1] data]
[k1 (into {}
(for [[k2 v2] v1]
v2))])))
with result:
(delete-intermediate-level my-data) =>
{:data-0
{:type "Specialist",
:name "Dr Spongebob",
:illness "dehydration",
:ward-room "a1"},
:data-1
{:type "GP",
:name "Dr Patrick",
:illness "fishy eyes",
:ward-room "b5"}}
If my-list is supposed to be defined as
(def my-list
{:data-0
{:a1 ;;this is the value for :ward-room
{:type "Specialist"
:name "Dr Spongebob"
:illness "dehydration"
:ward-room "a1"}}
:data-1
{:b5
{:type "GP"
:name "Dr Patrick"
:illness "fishy eyes"
:ward-room "b5"}}})
(that is, if we include the :ward-room key and value in the :b5 map rather than having it floating around on the loose) then the quickest way I can see to do this is:
(zipmap (keys my-list) (map #(first (vals %)) (vals my-list)))
It we wrap the above in a (pprint...) form it returns
{:data-0
{:type "Specialist",
:name "Dr Spongebob",
:illness "dehydration",
:ward-room "a1"},
:data-1
{:type "GP",
:name "Dr Patrick",
:illness "fishy eyes",
:ward-room "b5"}}
EDIT
Or if you prefer it in thread-last form you can use
(->> my-list
(vals)
(map #(first (vals %)))
(zipmap (keys my-list)))

What is the Clojure way to transform following data?

So I've just played with Clojure today.
Using this data,
(def test-data
[{:id 35462, :status "COMPLETED", :p 2640000, :i 261600}
{:id 35462, :status "CREATED", :p 240000, :i 3200}
{:id 57217, :status "COMPLETED", :p 470001, :i 48043}
{:id 57217, :status "CREATED", :p 1409999, :i 120105}])
Then transform the above data with,
(as-> test-data input
(group-by :id input)
(map (fn [x] {:id (key x)
:p {:a (as-> (filter #(= (:status %) "COMPLETED") (val x)) tmp
(into {} tmp)
(get tmp :p))
:b (as-> (filter #(= (:status %) "CREATED") (val x)) tmp
(into {} tmp)
(get tmp :p))}
:i {:a (as-> (filter #(= (:status %) "COMPLETED") (val x)) tmp
(into {} tmp)
(get tmp :i))
:b (as-> (filter #(= (:status %) "CREATED") (val x)) tmp
(into {} tmp)
(get tmp :i))}})
input)
(into [] input))
To produce,
[{:id 35462, :p {:a 2640000, :b 240000}, :i {:a 261600, :b 3200}}
{:id 57217, :p {:a 470001, :b 1409999}, :i {:a 48043, :b 120105}}]
But I have a feeling that my code is not the "Clojure way". So my question is, what is the "Clojure way" to achieve what I've produced?
The only things that stand out to me are using as-> when ->> would work just as well, and some work being done redundantly, and some destructuring opportunities:
(defn aggregate [[id values]]
(let [completed (->> (filter #(= (:status %) "COMPLETED") values)
(into {}))
created (->> (filter #(= (:status %) "CREATED") values)
(into {}))]
{:id id
:p {:a (:p completed)
:b (:p created)}
:i {:a (:i completed)
:b (:i created)}}))
(->> test-data
(group-by :id)
(map aggregate))
=>
({:id 35462, :p {:a 2640000, :b 240000}, :i {:a 261600, :b 3200}}
{:id 57217, :p {:a 470001, :b 1409999}, :i {:a 48043, :b 120105}})
However, pouring those filtered values (which are maps themselves) into a map seems suspect to me. This is creating a last-one-wins scenario where the order of your test data affects the output. Try this to see how different orders of test-data affect output:
(into {} (filter #(= (:status %) "COMPLETED") (shuffle test-data)))
It's a pretty odd transformation, keys seem a little arbitrary and it's hard to generalise from n=2 (or indeed to know whether n ever > 2).
I'd use functional decomposition to factor out some of the commonality and get some traction. First of all let us transform the statuses into our keys...
(def status->ab {"COMPLETED" :a "CREATED" :b})
Then, with that in hand, I'd like an easy way of getting the "meat" outof the substructure. Here, for a given key into the data, I'm providing the content of the enclosing map for that key and a given group result.
(defn subgroup->subresult [k subgroup]
(apply array-map (mapcat #(vector (status->ab (:status %)) (k %)) subgroup)))
With this, the main transformer becomes much more tractable:
(defn group->result [group]
{
:id (key group)
:p (subgroup->subresult :p (val group))
:i (subgroup->subresult :i (val group))})
I wouldn't consider generalising across :p and :i for this - if you had more than two keys, then maybe I would generate a map of k -> the subgroup result and do some sort of reducing merge. Anyway, we have an answer:
(map group->result (group-by :id test-data))
;; =>
({:id 35462, :p {:b 240000, :a 2640000}, :i {:b 3200, :a 261600}}
{:id 57217, :p {:b 1409999, :a 470001}, :i {:b 120105, :a 48043}})
There are no one "Clojure way" (I guess you mean functional way) as it depends on how you decompose a problem.
Here is the way I will do:
(->> test-data
(map (juxt :id :status identity))
(map ->nested)
(apply deep-merge)
(map (fn [[id m]]
{:id id
:p (->ab-map m :p)
:i (->ab-map m :i)})))
;; ({:id 35462, :p {:a 2640000, :b 240000}, :i {:a 261600, :b 3200}}
;; {:id 57217, :p {:a 470001, :b 1409999}, :i {:a 48043, :b 120105}})
As you can see, I used a few functions and here is the step-by-step explanation:
Extract index keys (id + status) and the map itself into vector
(map (juxt :id :status identity) test-data)
;; ([35462 "COMPLETED" {:id 35462, :status "COMPLETED", :p 2640000, :i 261600}]
;; [35462 "CREATED" {:id 35462, :status "CREATED", :p 240000, :i 3200}]
;; [57217 "COMPLETED" {:id 57217, :status "COMPLETED", :p 470001, :i 48043}]
;; [57217 "CREATED" {:id 57217, :status "CREATED", :p 1409999, :i 120105}])
Transform into nested map (id, then status)
(map ->nested *1)
;; ({35462 {"COMPLETED" {:id 35462, :status "COMPLETED", :p 2640000, :i 261600}}}
;; {35462 {"CREATED" {:id 35462, :status "CREATED", :p 240000, :i 3200}}}
;; {57217 {"COMPLETED" {:id 57217, :status "COMPLETED", :p 470001, :i 48043}}}
;; {57217 {"CREATED" {:id 57217, :status "CREATED", :p 1409999, :i 120105}}})
Merge nested map by id
(apply deep-merge *1)
;; {35462
;; {"COMPLETED" {:id 35462, :status "COMPLETED", :p 2640000, :i 261600},
;; "CREATED" {:id 35462, :status "CREATED", :p 240000, :i 3200}},
;; 57217
;; {"COMPLETED" {:id 57217, :status "COMPLETED", :p 470001, :i 48043},
;; "CREATED" {:id 57217, :status "CREATED", :p 1409999, :i 120105}}}
For attribute :p and :i, map to :a and :b according to status
(->ab-map {"COMPLETED" {:id 35462, :status "COMPLETED", :p 2640000, :i 261600},
"CREATED" {:id 35462, :status "CREATED", :p 240000, :i 3200}}
:p)
;; => {:a 2640000, :b 240000}
And below are the few helper functions I used:
(defn ->ab-map [m k]
(zipmap [:a :b]
(map #(get-in m [% k]) ["COMPLETED" "CREATED"])))
(defn ->nested [[k & [v & r :as t]]]
{k (if (seq r) (->nested t) v)})
(defn deep-merge [& xs]
(if (every? map? xs)
(apply merge-with deep-merge xs)
(apply merge xs)))
I would approach it more like the following, so it can handle any number of entries for each :id value. Of course, many variations are possible.
(ns tst.demo.core
(:use demo.core tupelo.core tupelo.test)
(:require
[tupelo.core :as t] ))
(dotest
(let [test-data [{:id 35462, :status "COMPLETED", :p 2640000, :i 261600}
{:id 35462, :status "CREATED", :p 240000, :i 3200}
{:id 57217, :status "COMPLETED", :p 470001, :i 48043}
{:id 57217, :status "CREATED", :p 1409999, :i 120105}]
d1 (group-by :id test-data)
d2 (t/forv [[id entries] d1]
{:id id
:status-all (mapv :status entries)
:p-all (mapv :p entries)
:i-all (mapv :i entries)})]
(is= d1
{35462
[{:id 35462, :status "COMPLETED", :p 2640000, :i 261600}
{:id 35462, :status "CREATED", :p 240000, :i 3200}],
57217
[{:id 57217, :status "COMPLETED", :p 470001, :i 48043}
{:id 57217, :status "CREATED", :p 1409999, :i 120105}]})
(is= d2 [{:id 35462,
:status-all ["COMPLETED" "CREATED"],
:p-all [2640000 240000],
:i-all [261600 3200]}
{:id 57217,
:status-all ["COMPLETED" "CREATED"],
:p-all [470001 1409999],
:i-all [48043 120105]}])
))

Clojure parse nested vectors

I am looking to transform a clojure tree structure into a map with its dependencies
For example, an input like:
[{:value "A"}
[{:value "B"}
[{:value "C"} {:value "D"}]
[{:value "E"} [{:value "F"}]]]]
equivalent to:
:A
:B
:C
:D
:E
:F
output:
{:A [:B :E] :B [:C :D] :C [] :D [] :E [:F] :F}
I have taken a look at tree-seq and zippers but can't figure it out!
Here's a way to build up the desired map while using a zipper to traverse the tree. First let's simplify the input tree to match your output format (maps of :value strings → keywords):
(def tree
[{:value "A"}
[{:value "B"} [{:value "C"} {:value "D"}]
{:value "E"} [{:value "F"}]]])
(def simpler-tree
(clojure.walk/postwalk
#(if (map? %) (keyword (:value %)) %)
tree))
;; [:A [:B [:C :D] :E [:F]]]
Then you can traverse the tree with loop/recur and clojure.zip/next, using two loop bindings: the current position in tree, and the map being built.
(loop [loc (z/vector-zip simpler-tree)
deps {}]
(if (z/end? loc)
deps ;; return map when end is reached
(recur
(z/next loc) ;; advance through tree
(if (z/branch? loc)
;; for (non-root) branches, add top-level key with direct descendants
(if-let [parent (some-> (z/prev loc) z/node)]
(assoc deps parent (filterv keyword? (z/children loc)))
deps)
;; otherwise add top-level key with no direct descendants
(assoc deps (z/node loc) [])))))
=> {:A [:B :E], :B [:C :D], :C [], :D [], :E [:F], :F []}
This is easy to do using the tupelo.forest library. I reformatted your source data to make it fit into the Hiccup syntax:
(dotest
(let [relationhip-data-hiccup [:A
[:B
[:C]
[:D]]
[:E
[:F]]]
expected-result {:A [:B :E]
:B [:C :D]
:C []
:D []
:E [:F]
:F []} ]
(with-debug-hid
(with-forest (new-forest)
(let [root-hid (tf/add-tree-hiccup relationhip-data-hiccup)
result (apply glue (sorted-map)
(forv [hid (all-hids)]
(let [parent-tag (grab :tag (hid->node hid))
kid-tags (forv [kid-hid (hid->kids hid)]
(let [kid-tag (grab :tag (hid->node kid-hid))]
kid-tag))]
{parent-tag kid-tags})))]
(is= (format-paths (find-paths root-hid [:A]))
[[{:tag :A}
[{:tag :B} [{:tag :C}] [{:tag :D}]]
[{:tag :E} [{:tag :F}]]]])
(is= result expected-result ))))))
API docs are here. The project README (in progress) is here. A video from the 2017 Clojure Conj is here.
You can see the above live code in the project repo.

How best to update this tree?

I've got the following tree:
{:start_date "2014-12-07"
:data {
:people [
{:id 1
:projects [{:id 1} {:id 2}]}
{:id 2
:projects [{:id 1} {:id 3}]}
]
}
}
I want to update the people and projects subtrees by adding a :name key-value pair.
Assuming I have these maps to perform the lookup:
(def people {1 "Susan" 2 "John")
(def projects {1 "Foo" 2 "Bar" 3 "Qux")
How could I update the original tree so that I end up with the following?
{:start_date "2014-12-07"
:data {
:people [
{:id 1
:name "Susan"
:projects [{:id 1 :name "Foo"} {:id 2 :name "Bar"}]}
{:id 2
:name "John"
:projects [{:id 1 :name "Foo"} {:id 3 :name "Qux"}]}
]
}
}
I've tried multiple combinations of assoc-in, update-in, get-in and map calls, but haven't been able to figure this out.
I have used letfn to break down the update into easier to understand units.
user> (def tree {:start_date "2014-12-07"
:data {:people [{:id 1
:projects [{:id 1} {:id 2}]}
{:id 2
:projects [{:id 1} {:id 3}]}]}})
#'user/tree
user> (def people {1 "Susan" 2 "John"})
#'user/people
user> (def projects {1 "Foo" 2 "Bar" 3 "Qux"})
#'user/projects
user>
(defn integrate-tree
[tree people projects]
;; letfn is like let, but it creates fn, and allows forward references
(letfn [(update-person [person]
;; -> is the "thread first" macro, the result of each expression
;; becomes the first arg to the next
(-> person
(assoc :name (people (:id person)))
(update-in [:projects] update-projects)))
(update-projects [all-projects]
(mapv
#(assoc % :name (projects (:id %)))
all-projects))]
(update-in tree [:data :people] #(mapv update-person %))))
#'user/integrate-tree
user> (pprint (integrate-tree tree people projects))
{:start_date "2014-12-07",
:data
{:people
[{:projects [{:name "Foo", :id 1} {:name "Bar", :id 2}],
:name "Susan",
:id 1}
{:projects [{:name "Foo", :id 1} {:name "Qux", :id 3}],
:name "John",
:id 2}]}}
nil
Not sure if entirely the best approach:
(defn update-names
[tree people projects]
(reduce
(fn [t [id name]]
(let [person-idx (ffirst (filter #(= (:id (second %)) id)
(map-indexed vector (:people (:data t)))))
temp (assoc-in t [:data :people person-idx :name] name)]
(reduce
(fn [t [id name]]
(let [project-idx (ffirst (filter #(= (:id (second %)) id)
(map-indexed vector (get-in t [:data :people person-idx :projects]))))]
(if project-idx
(assoc-in t [:data :people person-idx :projects project-idx :name] name)
t)))
temp
projects)))
tree
people))
Just call it with your parameters:
(clojure.pprint/pprint (update-names tree people projects))
{:start_date "2014-12-07",
:data
{:people
[{:projects [{:name "Foo", :id 1} {:name "Bar", :id 2}],
:name "Susan",
:id 1}
{:projects [{:name "Foo", :id 1} {:name "Qux", :id 3}],
:name "John",
:id 2}]}}
With nested reduces
Reduce over the people to update corresponding names
For each people, reduce over projects to update corresponding names
The noisesmith solution looks better since doesn't need to find person index or project index for each step.
Naturally you tried to assoc-in or update-in but the problem lies in your tree structure, since the key path to update John name is [:data :people 1 :name], so your assoc-in code would look like:
(assoc-in tree [:data :people 1 :name] "John")
But you need to find John's index in the people vector before you can update it, same things happens with projects inside.