Update 99designs/gqlgen@v0.17.62 and vektah/gqlparser/v2@v2.5.21 #609

StevenACoffman · 2024-12-30T18:20:19Z

Update gqlgen and gqlparser

This updates gqlgen and gqlparser to the latest versions github.com/99designs/gqlgen@v0.17.61 and github.com/vektah/gqlparser/v2@v2.5.21

In https://github.com/ent/contrib/pull/607/files github.com/99designs/gqlgen was moved from v0.17.48 to v0.17.51.

I see that in that PR it has a comment that says that gqlgen version v0.17.52 has an issue with ent field collection. It blames commit: 99designs/gqlgen@f81239e

The blamed gqlgen commit was merged 99designs/gqlgen#3287
This was to fix 99designs/gqlgen#3285 by reverting 99designs/gqlgen#3203

Currently gqlgen v0.17.61 is the latest. It is not clear to me if there remains any problem with gqlgen and ent field collection.
Please point me to an open issue in gqlgen (or PR) describing (or fixing) the ent field collection problem.

…parser/v2@v2.5.21 Signed-off-by: Steve Coffman <steve@khanacademy.org>

Signed-off-by: Steve Coffman <steve@khanacademy.org>

StevenACoffman · 2024-12-31T18:47:33Z

Hmmm, I'm not sure if my local environment is entirely what is expected. I appear to be finding the required local setup by process of elimination. Sorry for all the git commit amend and force pushing!

I'll try to instead to do this step by step and record what I'm doing in case it is helpful to some later person (e.g. future me). So far:

export GOBIN=~/go/bin
go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.28.0
go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@v1.2.0
cd entproto/cmd/protoc-gen-entgrpc
go install
cd ../../..
cd entproto/cmd/protoc-gen-ent
go install
cd ../../..
go generate ./...

This still results in a difference because protoc v3.19.4 is not the same as protoc v3.4.0

So I downloaded and decompressed protoc v3.19.4, prefixed my PATH environment variable with that bin directory, and tried again at this point.

this still results in one local test failing:

--- FAIL: TestPrintAddImport (0.83s)
    printer_test.go:103:
        	Error Trace:	/Users/steve/Documents/git/ent-contrib/schemast/printer_test.go:103
        	Error:      	Not equal:
        	            	expected: 0
        	            	actual  : 1
        	Test:       	TestPrintAddImport

Signed-off-by: Steve Coffman <steve@khanacademy.org>

StevenACoffman · 2024-12-31T19:29:32Z

Ok, I am getting go generate failures when I run nektos/act to simulate the remote GitHub action failures:

act -j generate

This provides this minor output tweak:

| diff --git a/entgql/internal/todogotype/generated.go b/entgql/internal/todogotype/generated.go
| index dd27c93..d9738af 100644
| --- a/entgql/internal/todogotype/generated.go
| +++ b/entgql/internal/todogotype/generated.go
| @@ -20630,7 +20630,7 @@ func (ec *executionContext) marshalOInt2ᚖint(ctx context.Context, sel ast.Sele
|  	return res
|  }
|
| -func (ec *executionContext) unmarshalOMap2map(ctx context.Context, v any) (map[string]any, error) {
| +func (ec *executionContext) unmarshalOMap2map(ctx context.Context, v any) (map[string]interface{}, error) {
|  	if v == nil {
|  		return nil, nil
|  	}
| @@ -20638,7 +20638,7 @@ func (ec *executionContext) unmarshalOMap2map(ctx context.Context, v any) (map[s
|  	return res, graphql.ErrorOnPath(ctx, err)
|  }
|
| -func (ec *executionContext) marshalOMap2map(ctx context.Context, sel ast.SelectionSet, v map[string]any) graphql.Marshaler {
| +func (ec *executionContext) marshalOMap2map(ctx context.Context, sel ast.SelectionSet, v map[string]interface{}) graphql.Marshaler {
|  	if v == nil {
|  		return graphql.Null
|  	}
[Continuous Integration/generate]   ❌  Failure - Main Check generated files
[Continuous Integration/generate] exitcode '1': failure
[Continuous Integration/generate]   🐳  docker exec cmd=[/opt/acttoolcache/node/18.20.5/arm64/bin/node /var/run/act/workflow/hashfiles/index.js] user= workdir=
[Continuous Integration/generate] 🏁  Job failed

Signed-off-by: Steve Coffman <steve@khanacademy.org>

StevenACoffman · 2024-12-31T20:16:54Z

Ok, moved to gqlgen v0.17.62 to make any/interface consistent

Signed-off-by: Steve Coffman <steve@khanacademy.org>

StevenACoffman · 2025-01-02T01:51:10Z

Running go test ./... causes the go.mod to add github.com/google/addlicense, but go mod tidy (which is in the go generate ./... ci job) removes it from a direct dependency (and moves it to an indirect). This causes a race condition if you locally run the ci github actions in the wrong order using nektos/act. Previously, I committed the go.mod and was puzzled over why the CI checks kept flagging changing go.mod / go.sum. To work around that, I'm adding a tools.go file (which will be useless in Go 1.24).

The other discrepancy is that my locally running go generate ./... seems to do something different for me using Go 1.23.4 on darwin/arm64 vs. when I run act -j generate --container-architecture linux/amd64. The remaining difference is between any and interface{} which I find surprising.

diff --git a/entgql/internal/todogotype/generated.go b/entgql/internal/todogotype/generated.go
index 76712c9..0e24fdf 100644
--- a/entgql/internal/todogotype/generated.go
+++ b/entgql/internal/todogotype/generated.go
@@ -20258,7 +20258,7 @@ func (ec *executionContext) marshalOInt2ᚖint(ctx context.Context, sel ast.Sele
 	return res
 }
 
-func (ec *executionContext) unmarshalOMap2map(ctx context.Context, v any) (map[string]any, error) {
+func (ec *executionContext) unmarshalOMap2map(ctx context.Context, v any) (map[string]interface{}, error) {
 	if v == nil {
 		return nil, nil
 	}
@@ -[20](https://github.com/ent/contrib/actions/runs/12564902369/job/35044421968?pr=609#step:11:21)266,7 +20266,7 @@ func (ec *executionContext) unmarshalOMap2map(ctx context.Context, v any) (map[s
 	return res, graphql.ErrorOnPath(ctx, err)
 }
 
-func (ec *executionContext) marshalOMap2map(ctx context.Context, sel ast.SelectionSet, v map[string]any) graphql.Marshaler {
+func (ec *executionContext) marshalOMap2map(ctx context.Context, sel ast.SelectionSet, v map[string]interface{}) graphql.Marshaler {
 	if v == nil {
 		return graphql.Null
 	}

Signed-off-by: Steve Coffman <steve@khanacademy.org>

StevenACoffman · 2025-01-02T02:37:27Z

So there was a slight discrepancy in the go.sum between my local go mod tidy and the nektos/act -j generate one, so I ran go clean --modcache && go mod tidy and that seemed to clear it up.

Now my nektos -j generate passes locally, as does nektos -j test so hopefully tomorrow when someone approves this it will just work in GitHub action runner as well.

a8m · 2025-01-02T12:30:53Z

Thanks for your contribution, @StevenACoffman 🙏🏻

michaelcaulley · 2025-01-06T16:16:02Z

@StevenACoffman, adding an additional thanks for helping with this. I really appreciate all your work on gqlgen!

michaelcaulley · 2025-01-08T15:11:26Z

entgql/internal/todo/gqlgen.yml

@@ -9,6 +9,7 @@ schema:

 resolver:
  layout: follow-schema
+  preserve_resolver: true


Did we want this to be true or false?

I picked true to be safe, because it depends. If there is customized code in those resolvers, then we want to preserve them (true), so we do not want to overwrite them. If there is nothing customized, then I guess it's harmless to preserve them, but we could set it to false.

I took this to be more of an example, as you people aren't actively changing these (or the schema) on a regular basis.

StevenACoffman · 2025-01-08T23:01:14Z

@michaelcaulley Hey, so we should probably bump gqlgen again after this, or else swap the models to use any instead of interface{} or there is a potential for inconsistent results prior to v0.17.63

michaelcaulley · 2025-01-09T21:29:26Z

If it's set to true, new ent schemas will not be added when running go generate .

If helpful, I can create a PR to update preserve_resolver to false and bump gqlgen.

@a8m or @giautm , can you confirm my thinking for preserve_resolver: ?

Edit: Here's the PR #610

…v2.5.21 (ent#609) * Update github.com/99designs/gqlgen@v0.17.61 and github.com/vektah/gqlparser/v2@v2.5.21 Signed-off-by: Steve Coffman <steve@khanacademy.org> * Re-generate Signed-off-by: Steve Coffman <steve@khanacademy.org> * Re-generate with correct protobuf versions Signed-off-by: Steve Coffman <steve@khanacademy.org> * Try again with protoc v3.19.4 Signed-off-by: Steve Coffman <steve@khanacademy.org> * minor tweak to go.mod and avoid pager getting stuck Signed-off-by: Steve Coffman <steve@khanacademy.org> * Update gqlgen to v0.17.62 Signed-off-by: Steve Coffman <steve@khanacademy.org> * regenerate? Signed-off-by: Steve Coffman <steve@khanacademy.org> * Minor tweak Signed-off-by: Steve Coffman <steve@khanacademy.org> * re-re-generate Signed-off-by: Steve Coffman <steve@khanacademy.org> * Add tools.go and run go mod tidy Signed-off-by: Steve Coffman <steve@khanacademy.org> * Generate using nektos/act -j generate Signed-off-by: Steve Coffman <steve@khanacademy.org> * Go generate again Signed-off-by: Steve Coffman <steve@khanacademy.org> * Generate using nektos/act -j generate Signed-off-by: Steve Coffman <steve@khanacademy.org> * go clean --modcache and then go mod tidy Signed-off-by: Steve Coffman <steve@khanacademy.org> --------- Signed-off-by: Steve Coffman <steve@khanacademy.org>

Update github.com/99designs/gqlgen@v0.17.61 and github.com/vektah/gql…

a00ecb7

…parser/v2@v2.5.21 Signed-off-by: Steve Coffman <steve@khanacademy.org>

StevenACoffman mentioned this pull request Dec 30, 2024

chore: bump go to 1.23.4 and gqlgen to v0.17.51 #607

Merged

Re-generate

ad5cd7e

Signed-off-by: Steve Coffman <steve@khanacademy.org>

StevenACoffman force-pushed the update_gqlgen_v0_17_61 branch from bb91180 to ad5cd7e Compare December 31, 2024 16:09

Re-generate with correct protobuf versions

a634de9

Signed-off-by: Steve Coffman <steve@khanacademy.org>

StevenACoffman force-pushed the update_gqlgen_v0_17_61 branch from 40ff9de to a634de9 Compare December 31, 2024 18:37

StevenACoffman added 2 commits December 31, 2024 14:02

Try again with protoc v3.19.4

61eb6d0

Signed-off-by: Steve Coffman <steve@khanacademy.org>

minor tweak to go.mod and avoid pager getting stuck

8000

a10df88

Signed-off-by: Steve Coffman <steve@khanacademy.org>

Update gqlgen to v0.17.62

efd3b5e

Signed-off-by: Steve Coffman <steve@khanacademy.org>

StevenACoffman changed the title ~~Update 99designs/gqlgen@v0.17.61 and vektah/gqlparser/v2@v2.5.21~~ Update 99designs/gqlgen@v0.17.62 and vektah/gqlparser/v2@v2.5.21 Dec 31, 2024

regenerate?

af62098

Signed-off-by: Steve Coffman <steve@khanacademy.org>

StevenACoffman force-pushed the update_gqlgen_v0_17_61 branch from e140af1 to af62098 Compare December 31, 2024 20:45

Minor tweak

7ce01a6

Signed-off-by: Steve Coffman <steve@khanacademy.org>

StevenACoffman force-pushed the update_gqlgen_v0_17_61 branch from ecb290d to 7ce01a6 Compare December 31, 2024 20:57

StevenACoffman added 2 commits December 31, 2024 18:22

re-re-generate

e687133

Signed-off-by: Steve Coffman <steve@khanacademy.org>

Add tools.go and run go mod tidy

aa94fb3

Signed-off-by: Steve Coffman <steve@khanacademy.org>

StevenACoffman added 4 commits January 1, 2025 20:56

Generate using nektos/act -j generate

3946427

Signed-off-by: Steve Coffman <steve@khanacademy.org>

Go generate again

e12243e

Signed-off-by: Steve Coffman <steve@khanacademy.org>

Generate using nektos/act -j generate

7d6f614

Signed-off-by: Steve Coffman <steve@khanacademy.org>

go clean --modcache and then go mod tidy

0530902

Signed-off-by: Steve Coffman <steve@khanacademy.org>

a8m approved these changes Jan 2, 2025

View reviewed changes

a8m merged commit 6ecb3d5 into ent:master Jan 2, 2025
4 checks passed

StevenACoffman deleted the update_gqlgen_v0_17_61 branch January 2, 2025 14:36

michaelcaulley reviewed Jan 8, 2025

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Update 99designs/gqlgen@v0.17.62 and vektah/gqlparser/v2@v2.5.21 #609

Update 99designs/gqlgen@v0.17.62 and vektah/gqlparser/v2@v2.5.21 #609

Update 99designs/gqlgen@v0.17.62 and vektah/gqlparser/v2@v2.5.21 #609

Update 99designs/gqlgen@v0.17.62 and vektah/gqlparser/v2@v2.5.21 #609

Conversation

Update gqlgen and gqlparser

Choose a reason for hiding this comment

Choose a reason for hiding this comment