Refactor: oss parser go refactor (#16391)

### What problem does this PR solve?

Package refactor and PDF post process.

### Type of change

- [x] Refactoring

---------

Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Jack
2026-06-29 18:46:41 +08:00
committed by GitHub
parent c0f64295c2
commit 98323e7910
119 changed files with 10771 additions and 9030 deletions

View File

@@ -226,8 +226,14 @@ jobs:
-v "${PWD}/internal/cpp/resource:/usr/share/infinity/resource" \
infiniflow/infinity_builder:ubuntu22_clang20
sudo docker exec "${BUILDER_CONTAINER}" bash -c 'git config --global safe.directory "*" && cd /ragflow && ./build.sh --cpp'
uv sync --python 3.13 --group test --frozen
./build.sh --go
- name: Prepare Python test environment
run: |
uv sync --python 3.13 --group test --frozen
uv pip install -e sdk/python
- name: Run Go unit tests
# Runs after `./build.sh --go`, which guarantees the C++ static
# library (librag_tokenizer_c_api.a) is present on disk. The Go
@@ -250,10 +256,7 @@ jobs:
PKGS=$(go list ./... 2>/dev/null \
| grep -v '/internal/storage$' \
| grep -v '/internal/tokenizer$' \
| grep -v '/internal/handler$' \
| grep -v '/internal/deepdoc/parser/pdf/pdfium' \
| grep -v '/internal/deepdoc/parser/pdf/pdfoxide' \
| grep -v '/internal/deepdoc/parser/pdf' || true)
| grep -v '/internal/handler$' || true)
if [ -z "$PKGS" ]; then
./build.sh --test
else
@@ -266,11 +269,6 @@ jobs:
sudo docker pull ubuntu:24.04
sudo DOCKER_BUILDKIT=1 docker build --build-arg NEED_MIRROR=1 --build-arg HTTPS_PROXY=${HTTPS_PROXY} --build-arg HTTP_PROXY=${HTTP_PROXY} -f Dockerfile -t ${RAGFLOW_IMAGE} .
- name: Prepare Python test environment
run: |
uv sync --python 3.13 --group test --frozen
uv pip install -e sdk/python
- name: Prepare function test environment
working-directory: docker
run: |
@@ -672,8 +670,14 @@ jobs:
-v "${PWD}/internal/cpp/resource:/usr/share/infinity/resource" \
infiniflow/infinity_builder:ubuntu22_clang20
sudo docker exec "${BUILDER_CONTAINER}" bash -c 'git config --global safe.directory "*" && cd /ragflow && ./build.sh --cpp'
uv sync --python 3.13 --group test --frozen
./build.sh --go
- name: Prepare Python test environment
run: |
uv sync --python 3.13 --group test --frozen
uv pip install -e sdk/python
- name: Run Go unit tests
# Runs after `./build.sh --go`, which guarantees the C++ static
# library (librag_tokenizer_c_api.a) is present on disk. The Go
@@ -696,10 +700,7 @@ jobs:
PKGS=$(go list ./... 2>/dev/null \
| grep -v '/internal/storage$' \
| grep -v '/internal/tokenizer$' \
| grep -v '/internal/handler$' \
| grep -v '/internal/deepdoc/parser/pdf/pdfium' \
| grep -v '/internal/deepdoc/parser/pdf/pdfoxide' \
| grep -v '/internal/deepdoc/parser/pdf' || true)
| grep -v '/internal/handler$' || true)
if [ -z "$PKGS" ]; then
./build.sh --test
else
@@ -712,11 +713,6 @@ jobs:
sudo docker pull ubuntu:24.04
sudo DOCKER_BUILDKIT=1 docker build --build-arg NEED_MIRROR=1 --build-arg HTTPS_PROXY=${HTTPS_PROXY} --build-arg HTTP_PROXY=${HTTP_PROXY} -f Dockerfile -t ${RAGFLOW_IMAGE} .
- name: Prepare Python test environment
run: |
uv sync --python 3.13 --group test --frozen
uv pip install -e sdk/python
- name: Prepare function test environment
working-directory: docker
run: |