fix: support all non-negative int64 deletion vector positions - #917

Summary

• replace dense high-32-bit bitmap storage with a sparse ordered map
• support every non-negative int64_t position through INT64_MAX without allocating intervening buckets
• serialize only populated buckets in ascending key order and normalize empty decoded buckets
• document that the half-open range API cannot include INT64_MAX, which must be added separately
• avoid overflow when a coalesced position-delete range ends at INT64_MAX
• reject deletion-vector payloads that exceed the signed 32-bit framing limit before allocating the complete serialized payload
• preflight every merged position index before creating the Puffin output, so an oversized first or later vector cannot leave an empty or partial file

Tracking issue: #916

Depends on #913. This branch includes the cross-language fixture commit from that PR and should remain draft until the dependency is resolved.

Test plan

• build/src/iceberg/test/util_test --gtest_filter='RoaringPositionBitmapTest.*:RoaringPositionBitmapInteropTest.*:PositionDeleteIndexTest.*:PositionDeleteRangeConsumerTest.*:DVWriterPreflightTest.*' (65 passed)
• build/src/iceberg/test/puffin_test (31 passed, including 5 cross-language DV fixtures)
• pre-commit run --all-files (passed)