[doc] Reuse cached artifacts. (#11560)

---------

Co-authored-by: Copilot <[email protected]>

Author: trivialfis

doc/conf.py

@@ -124,10 +124,18 @@ def try_fetch_jvm_doc(branch: str) -> bool:
         """
         try:
             local_jvm_docs = os.environ.get("XGBOOST_JVM_DOCS", None)
+            url = f"{S3_BUCKET}/{branch}/{commit}/{branch}.tar.bz2"
             if local_jvm_docs is not None:
-                filename = os.path.expanduser(local_jvm_docs)
+                local_jvm_docs = os.path.expanduser(local_jvm_docs)
+
+            if local_jvm_docs is not None and os.path.exists(local_jvm_docs):
+                # Reuse an existing tarball.
+                filename = local_jvm_docs
+            elif local_jvm_docs is not None:
+                # Download to local_jvm_docs for future reuse.
+                filename, _ = urllib.request.urlretrieve(url, filename=local_jvm_docs)
+                print(f"Finished: {url} -> {filename}")
             else:
-                url = f"{S3_BUCKET}/{branch}/{commit}/{branch}.tar.bz2"
                 filename, _ = urllib.request.urlretrieve(url)
                 print(f"Finished: {url} -> {filename}")
             if not os.path.exists(TMP_DIR):
@@ -161,10 +169,17 @@ def download_r_docs() -> None:
     def try_fetch_r_doc(branch: str) -> bool:
         try:
             local_r_docs = os.environ.get("XGBOOST_R_DOCS", None)
+            url = f"{S3_BUCKET}/{branch}/{commit}/r-docs-{branch}.tar.bz2"
             if local_r_docs is not None:
-                filename = os.path.expanduser(local_r_docs)
+                local_r_docs = os.path.expanduser(local_r_docs)
+
+            if local_r_docs is not None and os.path.exists(local_r_docs):
+                # Reuse an existing tarball.
+                filename = local_r_docs
+            elif local_r_docs is not None:
+                filename, _ = urllib.request.urlretrieve(url, filename=local_r_docs)
+                print(f"Finished: {url} -> {filename}")
             else:
-                url = f"{S3_BUCKET}/{branch}/{commit}/r-docs-{branch}.tar.bz2"
                 filename, _ = urllib.request.urlretrieve(url)
                 print(f"Finished: {url} -> {filename}")
 

doc/contrib/docs.rst

@@ -107,8 +107,12 @@ build directory. Following is a list of environment variables used by the fetche
 
  - ``READTHEDOCS``: Read the docs flag. Build the full documentation site including R, JVM and
    C doc when set to ``True`` (case sensitive).
- - ``XGBOOST_R_DOCS``: Local path for pre-built R document, used for development.
- - ``XGBOOST_JVM_DOCS``: Local path for pre-built JVM document, used for development.
+ - ``XGBOOST_R_DOCS``: Local path for pre-built R document, used for development. If it
+   points to a file that doesn't exist, the configuration script will download the
+   packaged document to that path for future reuse.
+ - ``XGBOOST_JVM_DOCS``: Local path for pre-built JVM document, used for
+   development. Similar to the R docs environment variable when it points to a non-existent
+   file.
 
 As of writing, RTD doesn't provide any facility to be embedded as a GitHub action but we
 need a way to specify the dependency between the CI pipelines and the document build in