@clickzetta/cz-cli-darwin-arm64 0.5.15 → 0.5.17

package/bin/skills/lakehouse-doc-en/references/zettapark-functions-guide.md

@@ -11,11 +11,11 @@ from clickzetta.zettapark.session import Session
 session = Session.builder.configs({
     "username": "your_username",
     "password": "your_password",
-    "service":  "cn-shanghai-alicloud.api.singdata.com",
+    "service":  "cn-shanghai-alicloud.api.clickzetta.com",
     "instance": "your_instance",
     "workspace": "your_workspace",
     "schema":   "public",
-    "vcluster": "default"
+    "vcluster": "DEFAULT"
 }).create()
 ```
 
@@ -25,8 +25,9 @@ Examples in each section use `create_dataframe` to create DataFrames directly fr
 
 ## String Functions
 
+Create sample data
+
 ```python
-# Create sample data
 df = session.create_dataframe(
     [(1, "Alice"), (2, "  hello world  "), (3, "bob")],
     schema=["id", "name"]
@@ -70,13 +71,16 @@ df.select(
     F.replace(F.col("name"), "world", "Lakehouse").alias("replaced"),
     F.regexp_replace(F.col("name"), r"\s+", "_").alias("no_space"),
 ).show()
-# +---+---------------+------------+---+------------------+---------------+
-# | id|          upper|        trim|len|          replaced|       no_space|
-# +---+---------------+------------+---+------------------+---------------+
-# |  1|  HELLO WORLD  | hello world| 11|  hello Lakehouse |_hello_world_  |
-# |  2|          ALICE|       Alice|  5|             Alice|          Alice|
-# |  3|            BOB|         bob|  3|               bob|            bob|
-# +---+---------------+------------+---+------------------+---------------+
+```
+
+```Plain
++---+---------------+------------+---+------------------+---------------+
+| id|          upper|        trim|len|          replaced|       no_space|
++---+---------------+------------+---+------------------+---------------+
+|  1|  HELLO WORLD  | hello world| 11|  hello Lakehouse |_hello_world_  |
+|  2|          ALICE|       Alice|  5|             Alice|          Alice|
+|  3|            BOB|         bob|  3|               bob|            bob|
++---+---------------+------------+---+------------------+---------------+
 ```
 
 ---
@@ -112,12 +116,15 @@ df.select(
     F.greatest(F.col("a"), F.col("b")).alias("max_ab"),
     F.least(F.col("a"), F.col("b")).alias("min_ab"),
 ).show()
-# +-----+----+-----+-------+------+------+
-# |round|ceil|floor|    abs|max_ab|min_ab|
-# +-----+----+-----+-------+------+------+
-# | 3.14|   4|    3|3.14159|   200|   100|
-# |-2.72|  -2|   -3|  2.718|   300|    50|
-# +-----+----+-----+-------+------+------+
+```
+
+```Plain
++-----+----+-----+-------+------+------+
+|round|ceil|floor|    abs|max_ab|min_ab|
++-----+----+-----+-------+------+------+
+| 3.14|   4|    3|3.14159|   200|   100|
+|-2.72|  -2|   -3|  2.718|   300|    50|
++-----+----+-----+-------+------+------+
 ```
 
 ---
@@ -162,32 +169,45 @@ df.select(
     F.last_day(F.to_date(F.col("dt_str"))).alias("last_day"),
     F.add_months(F.to_date(F.col("dt_str")), 1).alias("next_month"),
 ).show()
-# +----------+----+-----+----------+-----------+----------+----------+
-# |      date|year|month|   plus_7d|  formatted|  last_day|next_month|
-# +----------+----+-----+----------+-----------+----------+----------+
-# |2024-01-15|2024|    1|2024-01-22|2024/01/15 |2024-01-31|2024-02-15|
-# |2024-03-31|2024|    3|2024-04-07|2024/03/31 |2024-03-31|2024-04-30|
-# +----------+----+-----+----------+-----------+----------+----------+
+```
+
+```Plain
++----------+----+-----+----------+-----------+----------+----------+
+|      date|year|month|   plus_7d|  formatted|  last_day|next_month|
++----------+----+-----+----------+-----------+----------+----------+
+|2024-01-15|2024|    1|2024-01-22|2024/01/15 |2024-01-31|2024-02-15|
+|2024-03-31|2024|    3|2024-04-07|2024/03/31 |2024-03-31|2024-04-30|
++----------+----+-----+----------+-----------+----------+----------+
 ```
 
 ---
 
 ## Conditional Functions
 
+when / otherwise — multi-branch condition (like CASE WHEN)
+
 ```python
-# when / otherwise — multi-branch condition (like CASE WHEN)
 F.when(F.col("score") >= 90, "A") \
  .when(F.col("score") >= 80, "B") \
  .when(F.col("score") >= 60, "C") \
  .otherwise("F")
+```
 
-# iff — simple binary condition (like ternary operator)
+iff — simple binary condition (like ternary operator)
+
+```python
 F.iff(F.col("amount") > 0, "positive", "non-positive")
+```
 
-# coalesce — return the first non-NULL value
+coalesce — return the first non-NULL value
+
+```python
 F.coalesce(F.col("value"), F.col("default_value"), F.lit(0))
+```
 
-# is_null / is_not_null
+is\_null / is\_not\_null
+
+```python
 F.is_null(F.col("name"))
 ```
 
@@ -206,14 +226,17 @@ df.select(
      .otherwise("F").alias("grade"),
     F.iff(F.col("score") >= 60, "pass", "fail").alias("result"),
 ).show()
-# +---+-----+-----+------+
-# | id|score|grade|result|
-# +---+-----+-----+------+
-# |  1|   95|    A|  pass|
-# |  2|   82|    B|  pass|
-# |  3|   67|    C|  pass|
-# |  4|   45|    F|  fail|
-# +---+-----+-----+------+
+```
+
+```Plain
++---+-----+-----+------+
+| id|score|grade|result|
++---+-----+-----+------+
+|  1|   95|    A|  pass|
+|  2|   82|    B|  pass|
+|  3|   67|    C|  pass|
+|  4|   45|    F|  fail|
++---+-----+-----+------+
 ```
 
 ---
@@ -249,12 +272,15 @@ df.group_by("category").agg(
     F.max(F.col("amount")).alias("max"),
     F.min(F.col("amount")).alias("min"),
 ).show()
-# +--------+---+-----+-----+---+---+
-# |category|cnt|total|  avg|max|min|
-# +--------+---+-----+-----+---+---+
-# |       A|  3|  350|116.7|200| 50|
-# |       B|  2|  450|225.0|300|150|
-# +--------+---+-----+-----+---+---+
+```
+
+```Plain
++--------+---+-----+-----+---+---+
+|category|cnt|total|  avg|max|min|
++--------+---+-----+-----+---+---+
+|       A|  3|  350|116.7|200| 50|
+|       B|  2|  450|225.0|300|150|
++--------+---+-----+-----+---+---+
 ```
 
 ---
@@ -279,11 +305,14 @@ df.select(
     F.get_json_object(F.col("data"), "$.age").alias("age"),
     F.get_json_object(F.col("data"), "$.addr.city").alias("city"),
 ).show()
-# +-----+---+-------+
-# | name|age|   city|
-# +-----+---+-------+
-# |Alice| 30|Beijing|
-# +-----+---+-------+
+```
+
+```Plain
++-----+---+-------+
+| name|age|   city|
++-----+---+-------+
+|Alice| 30|Beijing|
++-----+---+-------+
 ```
 
 ---
@@ -318,4 +347,4 @@ F.typeof(F.col("value"))            # Return the data type name of a column
 |------|------|
 | [Zettapark DataFrame API Guide](zettapark-dataframe-guide.md) | Complete DataFrame operations guide |
 | [Zettapark Quick Start](zettapark-quick-start.md) | Installation and basic examples |
-| [SQL Functions Reference](../sql_functions/) | Complete list of Lakehouse built-in SQL functions |
+| [SQL Functions Reference](sql_functions/) | Complete list of Lakehouse built-in SQL functions |

package/bin/skills/lakehouse-doc-en/references/zettapark-quick-start.md

@@ -25,11 +25,11 @@ from clickzetta.zettapark.session import Session
 session = Session.builder.configs({
     "username": "your_username",
     "password": "your_password",
-    "service":  "cn-shanghai-alicloud.api.singdata.com",
+    "service":  "cn-shanghai-alicloud.api.clickzetta.com",
     "instance": "your_instance",
     "workspace": "your_workspace",
     "schema":   "public",
-    "vcluster": "default"
+    "vcluster": "DEFAULT"
 }).create()
 ```
 

package/bin/skills/lakehouse-doc-en/references/zettapark-stream-guide.md

@@ -13,11 +13,11 @@ from clickzetta.zettapark import functions as F
 session = Session.builder.configs({
     "username": "your_username",
     "password": "your_password",
-    "service":  "cn-shanghai-alicloud.api.singdata.com",
+    "service":  "cn-shanghai-alicloud.api.clickzetta.com",
     "instance": "your_instance",
     "workspace": "your_workspace",
     "schema":   "public",
-    "vcluster": "default"
+    "vcluster": "DEFAULT"
 }).create()
 ```
 
@@ -59,7 +59,7 @@ session.sql("""
 """).collect()
 ```
 
-> 💡 **Tip:** `change_tracking` must be enabled via `ALTER TABLE SET PROPERTIES`. Specifying it at table creation time has no effect.
+> 💡 `change_tracking` must be enabled via `ALTER TABLE SET PROPERTIES`. Specifying it at table creation time has no effect.
 
 ---
 
@@ -131,7 +131,7 @@ deletes = stream_df.filter(
 ).select("id")
 ```
 
-> ⚠️ **Note:** The `__change_type` column name contains double underscores. Reference it with backticks: `` F.col("`__change_type`") ``
+> ⚠️ The `__change_type` column name contains double underscores. Reference it with backticks: `` F.col("`__change_type`") ``
 
 ---
 

package/bin/skills/lakehouse-doc-en/references/zettapark-volume-guide.md

@@ -13,11 +13,11 @@ from clickzetta.zettapark import functions as F
 session = Session.builder.configs({
     "username": "your_username",
     "password": "your_password",
-    "service":  "cn-shanghai-alicloud.api.singdata.com",
+    "service":  "cn-shanghai-alicloud.api.clickzetta.com",
     "instance": "your_instance",
     "workspace": "your_workspace",
     "schema":   "public",
-    "vcluster": "default"
+    "vcluster": "DEFAULT"
 }).create()
 ```
 
@@ -36,8 +36,9 @@ session = Session.builder.configs({
 
 The examples in this guide use Named Volume (internal Volume), which requires no external storage mount and can be used immediately after creation:
 
+Create a Named Volume (one-time operation)
+
 ```python
-# Create a Named Volume (one-time operation)
 session.sql("CREATE VOLUME IF NOT EXISTS my_named_vol").collect()
 ```
 
@@ -51,17 +52,24 @@ session.sql("CREATE VOLUME IF NOT EXISTS my_named_vol").collect()
 
 ### Upload a Local File to a Volume
 
+Upload a single file
+
 ```python
-# Upload a single file
 result = session.file.put(
     "/local/path/data.csv",
     "volume://my_named_vol/data/data.csv",
     auto_compress=False
 )
 print(result)
-# [PutResult(source='/local/path/data.csv', target='/data/data.csv', source_size=1024, target_size=1024)]
+```
+
+```Plain
+[PutResult(source='/local/path/data.csv', target='/data/data.csv', source_size=1024, target_size=1024)]
+```
+
+Refresh the directory index after upload so session.read can see the new file
 
-# Refresh the directory index after upload so session.read can see the new file
+```python
 session.sql("ALTER VOLUME my_named_vol REFRESH").collect()
 ```
 
@@ -73,7 +81,10 @@ result = session.file.get(
     "/local/output/"
 )
 print(result)
-# [GetResult(file='data.csv', size=1024)]
+```
+
+```Plain
+[GetResult(file='data.csv', size=1024)]
 ```
 
 ### List a Volume Directory
@@ -82,17 +93,24 @@ print(result)
 files = session.file.list_("volume://my_named_vol/data/")
 for f in files:
     print(f.file, f.size)
-# data/orders.csv  2048
-# data/users.csv   1024
+```
+
+```Plain
+data/orders.csv  2048
+data/users.csv   1024
 ```
 
 ### Delete a Volume File
 
+Delete a single file
+
 ```python
-# Delete a single file
 session.file.delete("volume://my_named_vol/data/old_file.csv")
+```
+
+Delete a directory (deletes all files under it)
 
-# Delete a directory (deletes all files under it)
+```python
 session.file.delete("volume://my_named_vol/archive/")
 ```
 
@@ -114,8 +132,9 @@ df.printSchema()
 
 ### Read Parquet
 
+Read all Parquet files in a directory
+
 ```python
-# Read all Parquet files in a directory
 df = session.read.parquet("volume://my_named_vol/data/parquet_dir/")
 df.show()
 ```
@@ -160,10 +179,11 @@ df.write.copy_into_volume(
 
 Read raw files from a Volume, process them, write to a table, then export results back to a Volume:
 
+Step 1: Upload raw data to Volume
+
 ```python
 import csv
 
-# Step 1: Upload raw data to Volume
 raw_data = [
     ["order_id", "user_id", "product", "amount", "status"],
     [1001, 101, "iPhone",  7999.0, "paid"],
@@ -178,32 +198,50 @@ session.file.put(
     "volume://my_named_vol/raw/orders.csv",
     auto_compress=False
 )
+```
 
-# Refresh directory index so session.read can see the newly uploaded file
+Refresh the directory index so session.read can see the newly uploaded file
+
+```python
 session.sql("ALTER VOLUME my_named_vol REFRESH").collect()
+```
+
+Step 2: Read from Volume and clean data
 
-# Step 2: Read from Volume and clean data
+```python
 df = session.read \
     .option("header", True) \
     .option("infer_schema", True) \
     .csv("volume://my_named_vol/raw/orders.csv")
+```
 
-# Filter and transform
+Filter and transform
+
+```python
 paid_df = df.filter(F.col("status") == "paid") \
     .with_column("amount_with_tax", F.col("amount") * 1.13)
+```
+
+Step 3: Write to a Lakehouse table
 
-# Step 3: Write to a Lakehouse table
+```python
 paid_df.write.save_as_table("paid_orders", mode="overwrite")
 print(f"Written {paid_df.count()} records")
+```
+
+Step 4: Export processed results back to Volume
 
-# Step 4: Export processed results back to Volume
+```python
 session.table("paid_orders") \
     .write.copy_into_volume(
         "volume://my_named_vol/processed/paid_orders/",
         file_format_type="parquet"
     )
+```
 
-# Verify export
+Verify export results
+
+```python
 files = session.file.list_("volume://my_named_vol/processed/paid_orders/")
 print(f"Exported files: {[f.file for f in files]}")
 ```
@@ -214,25 +252,41 @@ print(f"Exported files: {[f.file for f in files]}")
 
 Named Volume is internal storage — no external dependencies required. Suitable for temporary storage and export scenarios.
 
+Create a Named Volume
+
 ```python
-# Create a Named Volume
 session.sql("CREATE VOLUME IF NOT EXISTS my_named_vol").collect()
+```
 
-# Upload a file (using SQL PUT command)
+Upload a file (using SQL PUT command)
+
+```python
 session.sql("PUT '/local/path/file.csv' TO VOLUME my_named_vol FILE 'data/file.csv'").collect()
+```
+
+List files
 
-# List files
+```python
 files = session.file.list_("volume://my_named_vol/")
 for f in files:
     print(f.file, f.size)
+```
 
-# Download a file
+Download a file
+
+```python
 session.file.get("volume://my_named_vol/data/file.csv", "/local/output/")
+```
 
-# Delete a file
+Delete a file
+
+```python
 session.file.delete("volume://my_named_vol/data/file.csv")
+```
+
+Export DataFrame to Named Volume
 
-# Export DataFrame to Named Volume
+```python
 df.write.copy_into_volume(
     "volume://my_named_vol/export/",
     file_format_type="csv",
@@ -246,16 +300,23 @@ df.write.copy_into_volume(
 
 User Volume is each user's personal storage space. `session.file` methods are not supported — use SQL commands instead:
 
+Upload to User Volume
+
 ```python
-# Upload to User Volume
 session.sql("PUT '/local/path/file.csv' TO USER VOLUME FILE 'subdir/file.csv'").collect()
+```
+
+List User Volume files
 
-# List User Volume files
+```python
 files = session.sql("SHOW USER VOLUME DIRECTORY").collect()
 for f in files:
     print(f["relative_path"], f["size"])
+```
 
-# Read from User Volume (via SQL SELECT FROM VOLUME)
+Read from User Volume (via SQL SELECT FROM VOLUME)
+
+```python
 df = session.sql("""
     SELECT * FROM USER VOLUME
     USING CSV
@@ -263,8 +324,11 @@ df = session.sql("""
     FILES('subdir/file.csv')
 """)
 df.show()
+```
+
+Download a User Volume file
 
-# Download a User Volume file
+```python
 session.sql("GET USER VOLUME FILE 'subdir/file.csv' TO '/local/output/'").collect()
 ```
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@clickzetta/cz-cli-darwin-arm64",
-  "version": "0.5.15",
+  "version": "0.5.17",
   "description": "cz-cli binary for macOS ARM64 (Apple Silicon)",
   "os": [
     "darwin"